subject:(reinforcement)

Delft University of Technology

1. Van Vliet, B. Accelerating flat reinforcement learning on a robot by using subgoals in a hierarchical framework:.

Degree: 2010, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:8dccd17c-4483-4abc-9d9b-540c801186ce

► Learning a motor skill task with Reinforcement Learning still takes a long time. A way to speed up the learning process with- out using much… (more)

Subjects/Keywords: Reinforcement

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Van Vliet, B. (2010). Accelerating flat reinforcement learning on a robot by using subgoals in a hierarchical framework:. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:8dccd17c-4483-4abc-9d9b-540c801186ce

Chicago Manual of Style (16^th Edition):

Van Vliet, B. “Accelerating flat reinforcement learning on a robot by using subgoals in a hierarchical framework:.” 2010. Masters Thesis, Delft University of Technology. Accessed February 25, 2020. http://resolver.tudelft.nl/uuid:8dccd17c-4483-4abc-9d9b-540c801186ce.

MLA Handbook (7^th Edition):

Van Vliet, B. “Accelerating flat reinforcement learning on a robot by using subgoals in a hierarchical framework:.” 2010. Web. 25 Feb 2020.

Vancouver:

Van Vliet B. Accelerating flat reinforcement learning on a robot by using subgoals in a hierarchical framework:. [Internet] [Masters thesis]. Delft University of Technology; 2010. [cited 2020 Feb 25]. Available from: http://resolver.tudelft.nl/uuid:8dccd17c-4483-4abc-9d9b-540c801186ce.

Council of Science Editors:

Van Vliet B. Accelerating flat reinforcement learning on a robot by using subgoals in a hierarchical framework:. [Masters Thesis]. Delft University of Technology; 2010. Available from: http://resolver.tudelft.nl/uuid:8dccd17c-4483-4abc-9d9b-540c801186ce

Oregon State University

2. Mehta, Neville. Hierarchical structure discovery and transfer in sequential decision problems.

Degree: PhD, Computer Science, 2011, Oregon State University

URL: http://hdl.handle.net/1957/25199

► Acting intelligently to efficiently solve sequential decision problems requires the ability to extract hierarchical structure from the underlying domain dynamics, exploit it for optimal or… (more)

▼ Acting intelligently to efficiently solve sequential decision problems requires the ability to extract hierarchical structure from the underlying domain dynamics, exploit it for optimal or near-optimal decision-making, and transfer it to related problems instead of solving every problem in isolation. This dissertation makes three contributions toward this goal. The first contribution is the introduction of two frameworks for the transfer of hierarchical structure in sequential decision problems. The MASH framework facilitates transfer among multiple agents coordinating within a domain. The VRHRL framework allows an agent to transfer its knowledge across a family of domains that share the same transition dynamics but have differing reward dynamics. Both MASH and VRHRL are validated empirically in large domains and the results demonstrate significant speedup in the solutions due to transfer. The second contribution is a new approach to the discovery of hierarchical structure in sequential decision problems. HI-MAT leverages action models to analyze the relevant dependencies in a hierarchically-generated trajectory and it discovers hierarchical structure that transfers to all problems whose actions share the same relevant dependencies as the single source problem. HierGen advances HI-MAT by learning simple action models, leveraging these models to analyze non-hierarchically-generated trajectories from multiple source problems in a robust causal fashion, and discovering hierarchical structure that transfers to all problems whose actions share the same causal dependencies as those in the source problems. Empirical evaluations in multiple domains demonstrate that the discovered hierarchical structures are comparable to manually-designed structures in quality and performance. Action models are essential to hierarchical structure discovery and other aspects of intelligent behavior. The third contribution of this dissertation is the introduction of two general frameworks for learning action models in sequential decision problems. In the MBP framework, learning is user-driven; in the PLEX framework, the learner generates its own problems. The frameworks are formally analyzed and reduced to concept learning with one-sided error. A general action-modeling language is shown to be efficiently learnable in both frameworks. Advisors/Committee Members: Tadepalli, Prasad (advisor), Dietterich, Thomas (committee member).

Subjects/Keywords: hierarchical reinforcement learning; Reinforcement learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Mehta, N. (2011). Hierarchical structure discovery and transfer in sequential decision problems. (Doctoral Dissertation). Oregon State University. Retrieved from http://hdl.handle.net/1957/25199

Chicago Manual of Style (16^th Edition):

Mehta, Neville. “Hierarchical structure discovery and transfer in sequential decision problems.” 2011. Doctoral Dissertation, Oregon State University. Accessed February 25, 2020. http://hdl.handle.net/1957/25199.

MLA Handbook (7^th Edition):

Mehta, Neville. “Hierarchical structure discovery and transfer in sequential decision problems.” 2011. Web. 25 Feb 2020.

Vancouver:

Mehta N. Hierarchical structure discovery and transfer in sequential decision problems. [Internet] [Doctoral dissertation]. Oregon State University; 2011. [cited 2020 Feb 25]. Available from: http://hdl.handle.net/1957/25199.

Council of Science Editors:

Mehta N. Hierarchical structure discovery and transfer in sequential decision problems. [Doctoral Dissertation]. Oregon State University; 2011. Available from: http://hdl.handle.net/1957/25199

Oregon State University

3. Proper, Scott. Scaling multiagent reinforcement learning.

Degree: PhD, Computer Science, 2009, Oregon State University

URL: http://hdl.handle.net/1957/13662

► Reinforcement learning in real-world domains suffers from three curses of dimensionality: explosions in state and action spaces, and high stochasticity or "outcome space" explosion. Multiagent… (more)

▼ Reinforcement learning in real-world domains suffers from three curses of dimensionality: explosions in state and action spaces, and high stochasticity or "outcome space" explosion. Multiagent domains are particularly susceptible to these problems. This thesis describes ways to mitigate these curses in several different multiagent domains, including real-time delivery of products using multiple vehicles with stochastic demands, a multiagent predator-prey domain, and a domain based on a real-time strategy game. To mitigate the problem of state-space explosion, this thesis present several approaches that mitigate each of these curses. "Tabular linear functions" (TLFs) are introduced that generalize tile-coding and linear value functions and allow learning of complex nonlinear functions in high-dimensional state-spaces. It is also shown how to adapt TLFs to relational domains, creating a "lifted" version called relational templates. To mitigate the problem of action-space explosion, the replacement of complete joint action space search with a form of hill climbing is described. To mitigate the problem of outcome space explosion, a more efficient calculation of the expected value of the next state is shown, and two real-time dynamic programming algorithms based on afterstates, ASH-learning and ATR-learning, are introduced. Lastly, two approaches that scale by treating a multiagent domain as being formed of several coordinating agents are presented. "Multiagent H-learning" and "Multiagent ASH-learning" are described, where coordination is achieved through a method called "serial coordination". This technique has the benefit of addressing each of the three curses of dimensionality simultaneously by reducing the space of states and actions each local agent must consider. The second approach to multiagent coordination presented is "assignment-based decomposition", which divides the action selection step into an assignment phase and a primitive action selection step. Like the multiagent approach, assignment-based decomposition addresses all three curses of dimensionality simultaneously by reducing the space of states and actions each group of agents must consider. This method is capable of much more sophisticated coordination. Experimental results are presented which show successful application of all methods described. These results demonstrate that the scaling techniques described in this thesis can greatly mitigate the three curses of dimensionality and allow solutions for multiagent domains to scale to large numbers of agents, and complex state and outcome spaces. Advisors/Committee Members: Tadepalli, Prasad (advisor), Dietterich, Thomas (committee member).

Subjects/Keywords: Reinforcement learning; Reinforcement learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Proper, S. (2009). Scaling multiagent reinforcement learning. (Doctoral Dissertation). Oregon State University. Retrieved from http://hdl.handle.net/1957/13662

Chicago Manual of Style (16^th Edition):

Proper, Scott. “Scaling multiagent reinforcement learning.” 2009. Doctoral Dissertation, Oregon State University. Accessed February 25, 2020. http://hdl.handle.net/1957/13662.

MLA Handbook (7^th Edition):

Proper, Scott. “Scaling multiagent reinforcement learning.” 2009. Web. 25 Feb 2020.

Vancouver:

Proper S. Scaling multiagent reinforcement learning. [Internet] [Doctoral dissertation]. Oregon State University; 2009. [cited 2020 Feb 25]. Available from: http://hdl.handle.net/1957/13662.

Council of Science Editors:

Proper S. Scaling multiagent reinforcement learning. [Doctoral Dissertation]. Oregon State University; 2009. Available from: http://hdl.handle.net/1957/13662

University of Illinois – Urbana-Champaign

4. Potok, Matthew. Safe reinforcement learning: An overview, a hybrid systems perspective, and a case study.

Degree: MS, Electrical & Computer Engr, 2018, University of Illinois – Urbana-Champaign

URL: http://hdl.handle.net/2142/102518

► Reinforcement learning (RL) is a general method for agents to learn optimal control policies through exploration and experience. Due to its generality, RL can generate… (more)

Subjects/Keywords: Reinforcement Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Potok, M. (2018). Safe reinforcement learning: An overview, a hybrid systems perspective, and a case study. (Thesis). University of Illinois – Urbana-Champaign. Retrieved from http://hdl.handle.net/2142/102518

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Potok, Matthew. “Safe reinforcement learning: An overview, a hybrid systems perspective, and a case study.” 2018. Thesis, University of Illinois – Urbana-Champaign. Accessed February 25, 2020. http://hdl.handle.net/2142/102518.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Potok, Matthew. “Safe reinforcement learning: An overview, a hybrid systems perspective, and a case study.” 2018. Web. 25 Feb 2020.

Vancouver:

Potok M. Safe reinforcement learning: An overview, a hybrid systems perspective, and a case study. [Internet] [Thesis]. University of Illinois – Urbana-Champaign; 2018. [cited 2020 Feb 25]. Available from: http://hdl.handle.net/2142/102518.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Potok M. Safe reinforcement learning: An overview, a hybrid systems perspective, and a case study. [Thesis]. University of Illinois – Urbana-Champaign; 2018. Available from: http://hdl.handle.net/2142/102518

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Oregon State University

5. Lauer, Christopher Joseph. Determining optimal timber harvest and fuel treatment on a fire-threatened landscape using approximate dynamic programming.

Degree: PhD, 2017, Oregon State University

URL: http://hdl.handle.net/1957/61678

► Forest management in the face of fire risk is a challenging problem because fire spreads across a landscape and because its occurrence is unpredictable. Additionally,… (more)

▼ Forest management in the face of fire risk is a challenging problem because fire spreads across a landscape and because its occurrence is unpredictable. Additionally, management must be adjusted over time as unpredictable fire events are realized. Land managers have some control over the vegetation conditions that facilitate fire spread, and they can engage in activity that reduces fire arrival probability and decreases the likelihood of damage. This management activity will have consequences for fire risk in multiple locations on a landscape over a long time-horizon. The first manuscript in this dissertation demonstrates a method for incorporating spatial information and interactions into a dynamic model for management decisions. Approximate dynamic programming is applied to determine the optimal timing and location of fuel treatments and timber harvests for a fire-threatened landscape. This method allows a value function and an optimal policy to be found for a problem with high dimension state and action spaces. Larger net present values can be achieved using policies that explicitly consider evolving spatial interactions created by fire spread, compared to policies that are optimal in a non-spatial or non-dynamic setting. The second manuscript explores the interaction of multiple landowners on a single landscape. Fuel conditions that allow fire to cross property boundaries creates externalities, and must be accounted for when making management decisions. In the second manuscript, the problem of determining optimal management is formulated as a dynamic game where each agent affects the fire risk for other agents on the landscape. Value functions and optimal policies that account for fire-spread externalities are determined for each agent. This method is applied to analyze the effect of ownership fragmentation on landowner welfare and ecological outcomes. The third manuscript explores policies designed to make landowners accountable for externalities generated by their management. Damage caused by spreading fires has prompted the creation of laws such as liability and negligence standards for landowners. Large damaging fires that resulted in expensive litigation have prompted changes to wildfire liability laws in several states. These regulations change the incentives that managers face. In this manuscript, the multi-agent framework developed in the second part of this dissertation is expanded and applied to analyze the effect of different types of liability regulations. Advisors/Committee Members: Montgomery, Claire A. (advisor), Dietterich, Thomas G. (committee member).

Subjects/Keywords: reinforcement learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lauer, C. J. (2017). Determining optimal timber harvest and fuel treatment on a fire-threatened landscape using approximate dynamic programming. (Doctoral Dissertation). Oregon State University. Retrieved from http://hdl.handle.net/1957/61678

Chicago Manual of Style (16^th Edition):

Lauer, Christopher Joseph. “Determining optimal timber harvest and fuel treatment on a fire-threatened landscape using approximate dynamic programming.” 2017. Doctoral Dissertation, Oregon State University. Accessed February 25, 2020. http://hdl.handle.net/1957/61678.

MLA Handbook (7^th Edition):

Lauer, Christopher Joseph. “Determining optimal timber harvest and fuel treatment on a fire-threatened landscape using approximate dynamic programming.” 2017. Web. 25 Feb 2020.

Vancouver:

Lauer CJ. Determining optimal timber harvest and fuel treatment on a fire-threatened landscape using approximate dynamic programming. [Internet] [Doctoral dissertation]. Oregon State University; 2017. [cited 2020 Feb 25]. Available from: http://hdl.handle.net/1957/61678.

Council of Science Editors:

Lauer CJ. Determining optimal timber harvest and fuel treatment on a fire-threatened landscape using approximate dynamic programming. [Doctoral Dissertation]. Oregon State University; 2017. Available from: http://hdl.handle.net/1957/61678

Delft University of Technology

6. Van Diepen, M.D.M. Avoiding failure states during reinforcement learning:.

Degree: 2011, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:1f03c580-9fd5-4807-87b5-d70890e05ff6

► The Delft Biorobotics Laboratory develops bipedal humanoid robots. One of these robots, called LEO, is designed to learn to walk using reinforcement learning. During learning,… (more)

▼ The Delft Biorobotics Laboratory develops bipedal humanoid robots. One of these robots, called LEO, is designed to learn to walk using reinforcement learning. During learning, LEO will make mistakes and fall. These mistakes can cause serious dam- age to the system but are an integral part of the learning process. A likely solution is punishing the robot more severely for falling. However, punishing the robot too rigorously can lead to a robot that is too cautious to make a step. In this research, three methods were tested that reduce the amount of falls during learning, without restricting the possible solutions or increasing the learning time. We introduce Threshold Restricted Learning (TRL), a new method for action se- lection that, during exploration, makes the probability an action is chosen dependent on the expected reward for taking that action. Actions with expected rewards below the set threshold have a signifcant reduced probability of being chosen. The concept of TRL developed from the desire to optimize the use of a pre-learned solution. Hence, TRL was tested after pre-learning in simulation. The largest reduction in the amount of falls achieved by TRL in this research was 50% TRL did not increase the learning time. Without pre-learning the largest reduction was 7%. Softmax action selection is a well known but underused selection method. Combined with pre-learning it was able to reduce the amount of falls during learning with approximately 80% and did not increase the learning time either. Without pre-learning, Softmax could still achieve a reduction of approximately 20%. Sarsa2Q, another new method, stores expected rewards at different levels op generalization. The level with little generalization is used to store the expected total positive reward, while the level with more generalization is used to store the expected total negative reward. Sarsa2Q learned to avoid the failure states for the inverted pendulum problem faster than using a single level of generalization. This method does not use pre-learning. The highest achieved reduction in the amount of falls was approximately 20%. Sarsa2Q can have a broader use than just avoiding failure states. Rather than only using the coarse generalization for negative rewards, it can be used for all rewards that need less precision. Advisors/Committee Members: Jonker, P.P., Schuitema, E..

Subjects/Keywords: reinforcement learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Van Diepen, M. D. M. (2011). Avoiding failure states during reinforcement learning:. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:1f03c580-9fd5-4807-87b5-d70890e05ff6

Chicago Manual of Style (16^th Edition):

Van Diepen, M D M. “Avoiding failure states during reinforcement learning:.” 2011. Masters Thesis, Delft University of Technology. Accessed February 25, 2020. http://resolver.tudelft.nl/uuid:1f03c580-9fd5-4807-87b5-d70890e05ff6.

MLA Handbook (7^th Edition):

Van Diepen, M D M. “Avoiding failure states during reinforcement learning:.” 2011. Web. 25 Feb 2020.

Vancouver:

Van Diepen MDM. Avoiding failure states during reinforcement learning:. [Internet] [Masters thesis]. Delft University of Technology; 2011. [cited 2020 Feb 25]. Available from: http://resolver.tudelft.nl/uuid:1f03c580-9fd5-4807-87b5-d70890e05ff6.

Council of Science Editors:

Van Diepen MDM. Avoiding failure states during reinforcement learning:. [Masters Thesis]. Delft University of Technology; 2011. Available from: http://resolver.tudelft.nl/uuid:1f03c580-9fd5-4807-87b5-d70890e05ff6

Delft University of Technology

7. Van Rooijen, J.C. Learning Parameter Selection in Continuous Reinforcement Learning: Attempting to Reduce Tuning Effords:.

Degree: 2012, Delft University of Technology

URL: http://resolver.tudelft.nl/uuid:94b81bc2-aff6-457f-9b54-be5e005def38

► The reinforcement learning (RL) framework enables to construct controllers that try to find find an optimal control strategy in an unknown environment by trial-and-error. After… (more)

▼ The reinforcement learning (RL) framework enables to construct controllers that try to find find an optimal control strategy in an unknown environment by trial-and-error. After selecting a control action, the controller receives a numerical reward. The reward signal is based on the current state of the environment and the applied control action. The controller aims to maximize the cumulative reward, known as the return. In this thesis actor-critic and criticonly RL algorithms are considered. Actor-critic algorithms consist of an element that selects the actions (the actor) and an element that learns the expectation of the return (the critic). This expectation is captured in a value function. The critic is used to improve the control policy of the actor. Critic-only algorithms select the action by direct optimization over a value function. Before a RL algorithm can be applied to a control problem, a number of learning parameters need to be set. The optimal values of some of these parameters are highly problem dependent. It is not straightforward how these parameters should be chosen and often these are often determined by trying a large set of parameters. The main focus of thesis is to devise an action selection method that is able to select continuous actions without problem dependent parameters. Two approaches are taken: first, it is investigated if Levenberg Marquardt (LM), a popular optimization method, can be used to determine the actor update step. Second, an action selection method is treated that lacks an explicit actor, called Value-Gradient Based Policy (VGBP). The LM algorithm uses the gradient and the Hessian to compute the update step. Therefore the policy gradient and Hessian need to be found. A novel actor-critic method has been devised, called Vanilla Actor-Critic (VAC), that efficiently learns the policy gradient. On the inverted pendulum swing-up task this algorithm outperformed Natural Actor-Critic (NAC). A number of different approaches have been taken to approximate the policy Hessian, but none delivered a proper Hessian estimate. Therefore, no LM actor update method was created. In VGBP the action is found by optimization of the right hand side of the Bellman equation. VGBP uses the provided reward function and a process model for this optimization. The process model is learned online using local linear regression (LLR). Due to the efficient use of information VGBP shows fast learning on the pendulum and a 2-DOF robotic arm. Advisors/Committee Members: Grondman, I., Babuska, R..

Subjects/Keywords: reinforcement learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Van Rooijen, J. C. (2012). Learning Parameter Selection in Continuous Reinforcement Learning: Attempting to Reduce Tuning Effords:. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:94b81bc2-aff6-457f-9b54-be5e005def38

Chicago Manual of Style (16^th Edition):

Van Rooijen, J C. “Learning Parameter Selection in Continuous Reinforcement Learning: Attempting to Reduce Tuning Effords:.” 2012. Masters Thesis, Delft University of Technology. Accessed February 25, 2020. http://resolver.tudelft.nl/uuid:94b81bc2-aff6-457f-9b54-be5e005def38.

MLA Handbook (7^th Edition):

Van Rooijen, J C. “Learning Parameter Selection in Continuous Reinforcement Learning: Attempting to Reduce Tuning Effords:.” 2012. Web. 25 Feb 2020.

Vancouver:

Van Rooijen JC. Learning Parameter Selection in Continuous Reinforcement Learning: Attempting to Reduce Tuning Effords:. [Internet] [Masters thesis]. Delft University of Technology; 2012. [cited 2020 Feb 25]. Available from: http://resolver.tudelft.nl/uuid:94b81bc2-aff6-457f-9b54-be5e005def38.

Council of Science Editors:

Van Rooijen JC. Learning Parameter Selection in Continuous Reinforcement Learning: Attempting to Reduce Tuning Effords:. [Masters Thesis]. Delft University of Technology; 2012. Available from: http://resolver.tudelft.nl/uuid:94b81bc2-aff6-457f-9b54-be5e005def38

University of Waikato

8. Lord, Sarah. Dog Behaviour - Effect of Delay To Reinforcement .

Degree: 2012, University of Waikato

URL: http://hdl.handle.net/10289/7039

► Dogs were fed dry food as reinforcement and were required to touch a wand with their nose to get that reinforcement. In the first study,… (more)

Subjects/Keywords: Reinforcement; Delay

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lord, S. (2012). Dog Behaviour - Effect of Delay To Reinforcement . (Masters Thesis). University of Waikato. Retrieved from http://hdl.handle.net/10289/7039

Chicago Manual of Style (16^th Edition):

Lord, Sarah. “Dog Behaviour - Effect of Delay To Reinforcement .” 2012. Masters Thesis, University of Waikato. Accessed February 25, 2020. http://hdl.handle.net/10289/7039.

MLA Handbook (7^th Edition):

Lord, Sarah. “Dog Behaviour - Effect of Delay To Reinforcement .” 2012. Web. 25 Feb 2020.

Vancouver:

Lord S. Dog Behaviour - Effect of Delay To Reinforcement . [Internet] [Masters thesis]. University of Waikato; 2012. [cited 2020 Feb 25]. Available from: http://hdl.handle.net/10289/7039.

Council of Science Editors:

Lord S. Dog Behaviour - Effect of Delay To Reinforcement . [Masters Thesis]. University of Waikato; 2012. Available from: http://hdl.handle.net/10289/7039

9. Frank, Mikhail Alexander. Learning to reach and reaching to learn: a unified approach to path planning and reactive control through reinforcement learning.

Degree: 2014, Università della Svizzera italiana

URL: http://doc.rero.ch/record/234387

► The next generation of intelligent robots will need to be able to plan reaches. Not just ballistic point to point reaches, but reaches around things… (more)

▼ The next generation of intelligent robots will need to be able to plan reaches. Not just ballistic point to point reaches, but reaches around things such as the edge of a table, a nearby human, or any other known object in the robot’s workspace. Planning reaches may seem easy to us humans, because we do it so intuitively, but it has proven to be a challenging problem, which continues to limit the versatility of what robots can do today. In this document, I propose a novel intrinsically motivated RL system that draws on both Path/Motion Planning and Reactive Control. Through Reinforcement Learning, it tightly integrates these two previously disparate approaches to robotics. The RL system is evaluated on a task, which is as yet unsolved by roboticists in practice. That is to put the palm of the iCub humanoid robot on arbitrary target objects in its workspace, start- ing from arbitrary initial configurations. Such motions can be generated by planning, or searching the configuration space, but this typically results in some kind of trajectory, which must then be tracked by a separate controller, and such an approach offers a brit- tle runtime solution because it is inflexible. Purely reactive systems are robust to many problems that render a planned trajectory infeasible, but lacking the capacity to search, they tend to get stuck behind constraints, and therefore do not replace motion planners. The planner/controller proposed here is novel in that it deliberately plans reaches without the need to track trajectories. Instead, reaches are composed of sequences of reactive motion primitives, implemented by my Modular Behavioral Environment (MoBeE), which provides (fictitious) force control with reactive collision avoidance by way of a realtime kinematic/geometric model of the robot and its workspace. Thus, to the best of my knowledge, mine is the first reach planning approach to simultaneously offer the best of both the Path/Motion Planning and Reactive Control approaches. By controlling the real, physical robot directly, and feeling the influence of the con- straints imposed by MoBeE, the proposed system learns a stochastic model of the iCub’s configuration space. Then, the model is exploited as a multiple query path planner to find sensible pre-reach poses, from which to initiate reaching actions. Experiments show that the system can autonomously find practical reaches to target objects in workspace and offers excellent robustness to changes in the workspace configuration as well as noise in the robot’s sensory-motor apparatus. Advisors/Committee Members: Schmidhuber, Jürgen (Dir.), Alexander (Codir.).

Subjects/Keywords: Reinforcement learning

11 more images…

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Frank, M. A. (2014). Learning to reach and reaching to learn: a unified approach to path planning and reactive control through reinforcement learning. (Thesis). Università della Svizzera italiana. Retrieved from http://doc.rero.ch/record/234387

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Frank, Mikhail Alexander. “Learning to reach and reaching to learn: a unified approach to path planning and reactive control through reinforcement learning.” 2014. Thesis, Università della Svizzera italiana. Accessed February 25, 2020. http://doc.rero.ch/record/234387.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Frank, Mikhail Alexander. “Learning to reach and reaching to learn: a unified approach to path planning and reactive control through reinforcement learning.” 2014. Web. 25 Feb 2020.

Vancouver:

Frank MA. Learning to reach and reaching to learn: a unified approach to path planning and reactive control through reinforcement learning. [Internet] [Thesis]. Università della Svizzera italiana; 2014. [cited 2020 Feb 25]. Available from: http://doc.rero.ch/record/234387.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Frank MA. Learning to reach and reaching to learn: a unified approach to path planning and reactive control through reinforcement learning. [Thesis]. Università della Svizzera italiana; 2014. Available from: http://doc.rero.ch/record/234387

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Louisiana State University

10. Alvarez, Jessica Pearl. Fixed-Time Schedule Effects on Participant Responding: An Evaluation Of Similar vs. Dissimilar Schedule Programs Using a Group Design Approach.

Degree: PhD, Psychology, 2014, Louisiana State University

URL: etd-06302014-190504 ; https://digitalcommons.lsu.edu/gradschool_dissertations/3565

► We evaluated the effectiveness of fixed-time (FT) schedules of reinforcement at eliminating participant’s responding using a between-subjects group design. Participants experienced one of three conditions;… (more)

Subjects/Keywords: fixed-time schedules; reinforcement; noncontingent reinforcement

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Alvarez, J. P. (2014). Fixed-Time Schedule Effects on Participant Responding: An Evaluation Of Similar vs. Dissimilar Schedule Programs Using a Group Design Approach. (Doctoral Dissertation). Louisiana State University. Retrieved from etd-06302014-190504 ; https://digitalcommons.lsu.edu/gradschool_dissertations/3565

Chicago Manual of Style (16^th Edition):

Alvarez, Jessica Pearl. “Fixed-Time Schedule Effects on Participant Responding: An Evaluation Of Similar vs. Dissimilar Schedule Programs Using a Group Design Approach.” 2014. Doctoral Dissertation, Louisiana State University. Accessed February 25, 2020. etd-06302014-190504 ; https://digitalcommons.lsu.edu/gradschool_dissertations/3565.

MLA Handbook (7^th Edition):

Alvarez, Jessica Pearl. “Fixed-Time Schedule Effects on Participant Responding: An Evaluation Of Similar vs. Dissimilar Schedule Programs Using a Group Design Approach.” 2014. Web. 25 Feb 2020.

Vancouver:

Alvarez JP. Fixed-Time Schedule Effects on Participant Responding: An Evaluation Of Similar vs. Dissimilar Schedule Programs Using a Group Design Approach. [Internet] [Doctoral dissertation]. Louisiana State University; 2014. [cited 2020 Feb 25]. Available from: etd-06302014-190504 ; https://digitalcommons.lsu.edu/gradschool_dissertations/3565.

Council of Science Editors:

Alvarez JP. Fixed-Time Schedule Effects on Participant Responding: An Evaluation Of Similar vs. Dissimilar Schedule Programs Using a Group Design Approach. [Doctoral Dissertation]. Louisiana State University; 2014. Available from: etd-06302014-190504 ; https://digitalcommons.lsu.edu/gradschool_dissertations/3565

SUNY College at Brockport

11. Rumfola, Lindsey. Positive Reinforcement Positively Helps Students in the Classroom.

Degree: MSEd, Education and Human Development, 2017, SUNY College at Brockport

URL: https://digitalcommons.brockport.edu/ehd_theses/786

► Current teachers are struggling between choosing mature teaching strategies and choosing more contemporary strategies to utilize in their classrooms. Although the choice to the… (more)

Subjects/Keywords: positive; reinforcement; positive reinforcement; behavior; students; Education

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Rumfola, L. (2017). Positive Reinforcement Positively Helps Students in the Classroom. (Thesis). SUNY College at Brockport. Retrieved from https://digitalcommons.brockport.edu/ehd_theses/786

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Rumfola, Lindsey. “Positive Reinforcement Positively Helps Students in the Classroom.” 2017. Thesis, SUNY College at Brockport. Accessed February 25, 2020. https://digitalcommons.brockport.edu/ehd_theses/786.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Rumfola, Lindsey. “Positive Reinforcement Positively Helps Students in the Classroom.” 2017. Web. 25 Feb 2020.

Vancouver:

Rumfola L. Positive Reinforcement Positively Helps Students in the Classroom. [Internet] [Thesis]. SUNY College at Brockport; 2017. [cited 2020 Feb 25]. Available from: https://digitalcommons.brockport.edu/ehd_theses/786.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Rumfola L. Positive Reinforcement Positively Helps Students in the Classroom. [Thesis]. SUNY College at Brockport; 2017. Available from: https://digitalcommons.brockport.edu/ehd_theses/786

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of North Texas

12. Reetz, Stephany Kristina. The Use of Conjugate Reinforcement in Autism Treatment Programs: a Demonstration and Discussion.

Degree: 2012, University of North Texas

URL: https://digital.library.unt.edu/ark:/67531/metadc177243/

► The effect of a reinforcer on behavior is largely determined by the schedule in which it is implemented. One type of reinforcement schedule that has… (more)

Subjects/Keywords: Conjugate reinforcement; reinforcement schedule; autism treatment

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Reetz, S. K. (2012). The Use of Conjugate Reinforcement in Autism Treatment Programs: a Demonstration and Discussion. (Thesis). University of North Texas. Retrieved from https://digital.library.unt.edu/ark:/67531/metadc177243/

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Reetz, Stephany Kristina. “The Use of Conjugate Reinforcement in Autism Treatment Programs: a Demonstration and Discussion.” 2012. Thesis, University of North Texas. Accessed February 25, 2020. https://digital.library.unt.edu/ark:/67531/metadc177243/.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Reetz, Stephany Kristina. “The Use of Conjugate Reinforcement in Autism Treatment Programs: a Demonstration and Discussion.” 2012. Web. 25 Feb 2020.

Vancouver:

Reetz SK. The Use of Conjugate Reinforcement in Autism Treatment Programs: a Demonstration and Discussion. [Internet] [Thesis]. University of North Texas; 2012. [cited 2020 Feb 25]. Available from: https://digital.library.unt.edu/ark:/67531/metadc177243/.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Reetz SK. The Use of Conjugate Reinforcement in Autism Treatment Programs: a Demonstration and Discussion. [Thesis]. University of North Texas; 2012. Available from: https://digital.library.unt.edu/ark:/67531/metadc177243/

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

13. Bodin, Vanessa G. A Framework for Analyzing Cultural Considerations in Working with Young Clients Diagnosed with Autism Spectrum Disorder.

Degree: Applied Behavior Analysis: M.S., Community Psychology, Counseling and Family Therapy, 2019, St. Cloud State University

URL: https://repository.stcloudstate.edu/cpcf_etds/68

► Culture consists of beliefs, laws, customs, and manners that society deems to be socially appropriate. As culture influences how the individual behaves within society,… (more)

Subjects/Keywords: culture; autism; edible reinforcement; praise; positive reinforcement

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Bodin, V. G. (2019). A Framework for Analyzing Cultural Considerations in Working with Young Clients Diagnosed with Autism Spectrum Disorder. (Masters Thesis). St. Cloud State University. Retrieved from https://repository.stcloudstate.edu/cpcf_etds/68

Chicago Manual of Style (16^th Edition):

Bodin, Vanessa G. “A Framework for Analyzing Cultural Considerations in Working with Young Clients Diagnosed with Autism Spectrum Disorder.” 2019. Masters Thesis, St. Cloud State University. Accessed February 25, 2020. https://repository.stcloudstate.edu/cpcf_etds/68.

MLA Handbook (7^th Edition):

Bodin, Vanessa G. “A Framework for Analyzing Cultural Considerations in Working with Young Clients Diagnosed with Autism Spectrum Disorder.” 2019. Web. 25 Feb 2020.

Vancouver:

Bodin VG. A Framework for Analyzing Cultural Considerations in Working with Young Clients Diagnosed with Autism Spectrum Disorder. [Internet] [Masters thesis]. St. Cloud State University; 2019. [cited 2020 Feb 25]. Available from: https://repository.stcloudstate.edu/cpcf_etds/68.

Council of Science Editors:

Bodin VG. A Framework for Analyzing Cultural Considerations in Working with Young Clients Diagnosed with Autism Spectrum Disorder. [Masters Thesis]. St. Cloud State University; 2019. Available from: https://repository.stcloudstate.edu/cpcf_etds/68

University of Aberdeen

14. Alexander, John W. Transfer in reinforcement learning.

Degree: PhD, 2015, University of Aberdeen

URL: http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=227908 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.675561

► The problem of developing skill repertoires autonomously in robotics and artificial intelligence is becoming ever more pressing. Currently, the issues of how to apply prior… (more)

▼ The problem of developing skill repertoires autonomously in robotics and artificial intelligence is becoming ever more pressing. Currently, the issues of how to apply prior knowledge to new situations and which knowledge to apply have not been sufficiently studied. We present a transfer setting where a reinforcement learning agent faces multiple problem solving tasks drawn from an unknown generative process, where each task has similar dynamics. The task dynamics are changed by varying in the transition function between states. The tasks are presented sequentially with the latest task presented considered as the target for transfer. We describe two approaches to solving this problem. Firstly we present an algorithm for transfer of the function encoding the stateaction value, defined as value function transfer. This algorithm uses the value function of a source policy to initialise the policy of a target task. We varied the type of basis the algorithm used to approximate the value function. Empirical results in several well known domains showed that the learners benefited from the transfer in the majority of cases. Results also showed that the Radial basis performed better in general than the Fourier. However contrary to expectation the Fourier basis benefited most from the transfer. Secondly, we present an algorithm for learning an informative prior which encodes beliefs about the underlying dynamics shared across all tasks. We call this agent the Informative Prior agent (IP). The prior is learnt though experience and captures the commonalities in the transition dynamics of the domain and allows for a quantification of the agent's uncertainty about these. By using a sparse distribution of the uncertainty in the dynamics as a prior, the IP agent can successfully learn a model of 1) the set of feasible transitions rather than the set of possible transitions, and 2) the likelihood of each of the feasible transitions. Analysis focusing on the accuracy of the learned model showed that IP had a very good accuracy bound, which is expressible in terms of only the permissible error and the diffusion, a factor that describes the concentration of the prior mass around the truth, and which decreases as the number of tasks experienced grows. The empirical evaluation of IP showed that an agent which uses the informative prior outperforms several existing Bayesian reinforcement learning algorithms on tasks with shared structure in a domain where multiple related tasks were presented only once to the learners. IP is a step towards the autonomous acquisition of behaviours in artificial intelligence. IP also provides a contribution towards the analysis of exploration and exploitation in the transfer paradigm.

Subjects/Keywords: Reinforcement learning; Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Alexander, J. W. (2015). Transfer in reinforcement learning. (Doctoral Dissertation). University of Aberdeen. Retrieved from http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=227908 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.675561

Chicago Manual of Style (16^th Edition):

Alexander, John W. “Transfer in reinforcement learning.” 2015. Doctoral Dissertation, University of Aberdeen. Accessed February 25, 2020. http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=227908 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.675561.

MLA Handbook (7^th Edition):

Alexander, John W. “Transfer in reinforcement learning.” 2015. Web. 25 Feb 2020.

Vancouver:

Alexander JW. Transfer in reinforcement learning. [Internet] [Doctoral dissertation]. University of Aberdeen; 2015. [cited 2020 Feb 25]. Available from: http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=227908 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.675561.

Council of Science Editors:

Alexander JW. Transfer in reinforcement learning. [Doctoral Dissertation]. University of Aberdeen; 2015. Available from: http://digitool.abdn.ac.uk:80/webclient/DeliveryManager?pid=227908 ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.675561

University of Hawaii

15. Zdep, Stanley Michael. Reinforcement of leadership behavior in specially-constructed groups.

Degree: PhD, 2009, University of Hawaii

URL: http://hdl.handle.net/10125/11904

►

Typescript.

Bibliography: leaves [78]-84.

viii, 84 l tables

Current interest in behavior modification through use of reinforcement principles recently has been extended to the area… (more)

▼

Typescript.

Bibliography: leaves [78]-84.

viii, 84 l tables

Current interest in behavior modification through use of reinforcement principles recently has been extended to the area of leadership behavior. Several studies have shown that it is possible to increase both participation and status of a selected person within a group by giving him positive reinforcement for leadership behaviors, while at the same time punishing these same behaviors in other persons within that group. The purpose of the present study was to investigate the effect of reinforcement in a group situation in which personality characteristics associated with leadership behavior were controlled. The CPI Leadership scale was administered to 177 student volunteers from introductory psychology classes at the University of Hawaii. ~s were then rank-ordered on the basis of these scores and assigned to one of four experimental conditions. A total of 36 four-person groups with nine groups per condition were formed. Half of the groups had target persons (TPs) with high leadership scores, and half had TPs with low scores. Using a factorial design, half of these TPs were reinforced for specified leadership behaviors and punished for silence (all reinforcement administered through individual earphones), while the other half received no reinforcement. Non-target persons (NTPs) in all groups had intermediate leadership scores, and they were punished (buzzer) for leadership behaviors and positively reinforced for agreeing with TP. The results indicated that high leadership TPs participated more in the discussion and were rated significantly higher on leadership behaviors by NTPs. All ratings were made on modified Bales interaction categories following the discussions. Moreover, it was possible to increase talking time significantly through reinforcement for high leadership TPs but not for low leadership TPs. This increased verbalization for high leadership TPs was maintained during unreinforced generalization sessions conducted 24 hours later. Reinforced high leadership TPs were rated higher than their non-reinforced counterparts on eight of the nine scales used, although individual mean differences were not significant. Among low leadership TPs, the reverse was true. Reinforced TPs were rated lower than TPs in the respective control condition, but again, the magnitude of the differences did not reach significance. These latter findings were explained in terms of nonverbal cues associated with punishment of TP for silence. Following reinforcement morale tended to be lower only in groups with reinforced low leadership TPs. In this latter case, it was not that NTPs resisted the reinforced TP, but rather that these TPs seemed to refuse to assume leadership responsibilities in the group. Groups with reinforced high leadership TPs reported the greatest satisfaction with the group product, while groups with reinforced low leadership TPs reported lowest satisfaction, although all ratings were above the "average" modulus (50%-ile) presented to Ss.

Subjects/Keywords: Leadership; Reinforcement (Psychology)

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Zdep, S. M. (2009). Reinforcement of leadership behavior in specially-constructed groups. (Doctoral Dissertation). University of Hawaii. Retrieved from http://hdl.handle.net/10125/11904

Chicago Manual of Style (16^th Edition):

Zdep, Stanley Michael. “Reinforcement of leadership behavior in specially-constructed groups.” 2009. Doctoral Dissertation, University of Hawaii. Accessed February 25, 2020. http://hdl.handle.net/10125/11904.

MLA Handbook (7^th Edition):

Zdep, Stanley Michael. “Reinforcement of leadership behavior in specially-constructed groups.” 2009. Web. 25 Feb 2020.

Vancouver:

Zdep SM. Reinforcement of leadership behavior in specially-constructed groups. [Internet] [Doctoral dissertation]. University of Hawaii; 2009. [cited 2020 Feb 25]. Available from: http://hdl.handle.net/10125/11904.

Council of Science Editors:

Zdep SM. Reinforcement of leadership behavior in specially-constructed groups. [Doctoral Dissertation]. University of Hawaii; 2009. Available from: http://hdl.handle.net/10125/11904

Anna University

16. Rajagopal S. Investigations on the effect of Reinforcement in exterior beamcolumn Joints under reversal loading;.

Degree: Investigations on the effect of Reinforcement in exterior beamcolumn Joints under reversal loading, 2015, Anna University

URL: http://shodhganga.inflibnet.ac.in/handle/10603/49573

►

Beam column joints are recognized as the most critical and newlinevulnerable zone of reinforced concrete RC moment resisting structure newlinesubject to seismic loads During an… (more)

Subjects/Keywords: Reinforcement in exterior

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

S, R. (2015). Investigations on the effect of Reinforcement in exterior beamcolumn Joints under reversal loading;. (Thesis). Anna University. Retrieved from http://shodhganga.inflibnet.ac.in/handle/10603/49573

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

S, Rajagopal. “Investigations on the effect of Reinforcement in exterior beamcolumn Joints under reversal loading;.” 2015. Thesis, Anna University. Accessed February 25, 2020. http://shodhganga.inflibnet.ac.in/handle/10603/49573.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

S, Rajagopal. “Investigations on the effect of Reinforcement in exterior beamcolumn Joints under reversal loading;.” 2015. Web. 25 Feb 2020.

Vancouver:

S R. Investigations on the effect of Reinforcement in exterior beamcolumn Joints under reversal loading;. [Internet] [Thesis]. Anna University; 2015. [cited 2020 Feb 25]. Available from: http://shodhganga.inflibnet.ac.in/handle/10603/49573.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

S R. Investigations on the effect of Reinforcement in exterior beamcolumn Joints under reversal loading;. [Thesis]. Anna University; 2015. Available from: http://shodhganga.inflibnet.ac.in/handle/10603/49573

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Louisiana State University

17. Alvarez, Jessica Pearl. Comparing extinction and noncontingent reinforcement under challenging conditions: the discriminative effects of reinforcement delivery.

Degree: MA, Psychology, 2011, Louisiana State University

URL: etd-03202012-125334 ; https://digitalcommons.lsu.edu/gradschool_theses/4178

► Extinction (EXT) and noncontingent reinforcement (NCR) procedures are commonly used to reduce problem behavior maintained by operant reinforcement. Both procedures reduce behavior by eliminating the… (more)

Subjects/Keywords: noncontingent reinforcement; extinction

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Alvarez, J. P. (2011). Comparing extinction and noncontingent reinforcement under challenging conditions: the discriminative effects of reinforcement delivery. (Masters Thesis). Louisiana State University. Retrieved from etd-03202012-125334 ; https://digitalcommons.lsu.edu/gradschool_theses/4178

Chicago Manual of Style (16^th Edition):

Alvarez, Jessica Pearl. “Comparing extinction and noncontingent reinforcement under challenging conditions: the discriminative effects of reinforcement delivery.” 2011. Masters Thesis, Louisiana State University. Accessed February 25, 2020. etd-03202012-125334 ; https://digitalcommons.lsu.edu/gradschool_theses/4178.

MLA Handbook (7^th Edition):

Alvarez, Jessica Pearl. “Comparing extinction and noncontingent reinforcement under challenging conditions: the discriminative effects of reinforcement delivery.” 2011. Web. 25 Feb 2020.

Vancouver:

Alvarez JP. Comparing extinction and noncontingent reinforcement under challenging conditions: the discriminative effects of reinforcement delivery. [Internet] [Masters thesis]. Louisiana State University; 2011. [cited 2020 Feb 25]. Available from: etd-03202012-125334 ; https://digitalcommons.lsu.edu/gradschool_theses/4178.

Council of Science Editors:

Alvarez JP. Comparing extinction and noncontingent reinforcement under challenging conditions: the discriminative effects of reinforcement delivery. [Masters Thesis]. Louisiana State University; 2011. Available from: etd-03202012-125334 ; https://digitalcommons.lsu.edu/gradschool_theses/4178

Louisiana State University

18. Lomas Mevers, Joanna Elizabeth. Treatment integrity failures matched to behavioral function.

Degree: PhD, Psychology, 2013, Louisiana State University

URL: etd-06192013-135121 ; https://digitalcommons.lsu.edu/gradschool_dissertations/357

► Prior research on treatment integrity has focused on either the lack of measurement of the independent variable (Peterson, Homer & Wonderlich, 1982; Gresham, Gansle &… (more)

Subjects/Keywords: compliance; prompting; reinforcement

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lomas Mevers, J. E. (2013). Treatment integrity failures matched to behavioral function. (Doctoral Dissertation). Louisiana State University. Retrieved from etd-06192013-135121 ; https://digitalcommons.lsu.edu/gradschool_dissertations/357

Chicago Manual of Style (16^th Edition):

Lomas Mevers, Joanna Elizabeth. “Treatment integrity failures matched to behavioral function.” 2013. Doctoral Dissertation, Louisiana State University. Accessed February 25, 2020. etd-06192013-135121 ; https://digitalcommons.lsu.edu/gradschool_dissertations/357.

MLA Handbook (7^th Edition):

Lomas Mevers, Joanna Elizabeth. “Treatment integrity failures matched to behavioral function.” 2013. Web. 25 Feb 2020.

Vancouver:

Lomas Mevers JE. Treatment integrity failures matched to behavioral function. [Internet] [Doctoral dissertation]. Louisiana State University; 2013. [cited 2020 Feb 25]. Available from: etd-06192013-135121 ; https://digitalcommons.lsu.edu/gradschool_dissertations/357.

Council of Science Editors:

Lomas Mevers JE. Treatment integrity failures matched to behavioral function. [Doctoral Dissertation]. Louisiana State University; 2013. Available from: etd-06192013-135121 ; https://digitalcommons.lsu.edu/gradschool_dissertations/357

University of New South Wales

19. Ismail, Hafsa. A neural network framework for combining different task types and motivations in motivated reinforcement learning.

Degree: Engineering & Information Technology, 2014, University of New South Wales

URL: http://handle.unsw.edu.au/1959.4/53975 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:12686/SOURCE02?view=true

► Combining different motivation models for different task types within artificial agents has the potential to produce agents capable of a greater range of behaviours in… (more)

▼ Combining different motivation models for different task types within artificial agents has the potential to produce agents capable of a greater range of behaviours in different situations. This thesis will explore the ability to produce agents that can identify different types of tasks online then learn solutions for these tasks while driven by one or more motivations in isolation or combination to produce different agent behaviour that will focus on different task types. The main contributions of this research are: Definitions for four task types for use in motivated reinforcement learning agents; a multi-layer neural network model for combining different motivations for different task types; a study of agent ability to identify different types of tasks in a simulated game scenario. A review of existing computational models of motivation and the layered approaches to the design of goal generation and intrinsically motivated learning agents inspire the multi-layer neural network framework presented and examined experimentally in this thesis. The first set of experiments examines topological and non-topological adaptive resonance theory networks that are used to classify sensed states and identify different types of tasks. Different distance metrics and weight update rules are used to determine the impact of the network structure on identified task types. The most promising network structure, distance metric and update rule is then chosen to implement the task identification process in conjunction with motivated reinforcement learning. In the second set of experiments, three motivation models, novelty, interest and competence, are examined separately in conjunction with our task identification algorithm. Established metrics and statistical methods are used to quantify learning behaviour and the complexity and variety of repetitive behavioural structures. Finally, we examine agent behaviour when the agent can identify more than one type of task with a single motive model that drives the learning process. Parallel and series task types combination modes are explored. Results show that a series approach to changing the type of task the agent can identify is most effective for producing motivated reinforcement learning agents that can both learn effectively and exhibit quantifiable changes in their characteristic learning behaviour over time. Advisors/Committee Members: Merrick, Kathryn, Engineering & Information Technology, Australian Defence Force Academy, UNSW, Barlow, Michael, Engineering & Information Technology, Australian Defence Force Academy, UNSW.

Subjects/Keywords: Motivated Reinforcement Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Ismail, H. (2014). A neural network framework for combining different task types and motivations in motivated reinforcement learning. (Masters Thesis). University of New South Wales. Retrieved from http://handle.unsw.edu.au/1959.4/53975 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:12686/SOURCE02?view=true

Chicago Manual of Style (16^th Edition):

Ismail, Hafsa. “A neural network framework for combining different task types and motivations in motivated reinforcement learning.” 2014. Masters Thesis, University of New South Wales. Accessed February 25, 2020. http://handle.unsw.edu.au/1959.4/53975 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:12686/SOURCE02?view=true.

MLA Handbook (7^th Edition):

Ismail, Hafsa. “A neural network framework for combining different task types and motivations in motivated reinforcement learning.” 2014. Web. 25 Feb 2020.

Vancouver:

Ismail H. A neural network framework for combining different task types and motivations in motivated reinforcement learning. [Internet] [Masters thesis]. University of New South Wales; 2014. [cited 2020 Feb 25]. Available from: http://handle.unsw.edu.au/1959.4/53975 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:12686/SOURCE02?view=true.

Council of Science Editors:

Ismail H. A neural network framework for combining different task types and motivations in motivated reinforcement learning. [Masters Thesis]. University of New South Wales; 2014. Available from: http://handle.unsw.edu.au/1959.4/53975 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:12686/SOURCE02?view=true

University of North Texas

20. Coulter, Laura E. The Effects of Increasing Rates of Reinforcement Through an Alternative Fluent Behavior on the Acquisition and Extinction of Behavior in Dogs.

Degree: 2012, University of North Texas

URL: https://digital.library.unt.edu/ark:/67531/metadc149576/

► The purpose of the present study was to experimentally investigate the effects of interspersing the opportunity to perform a fluent behavior during the acquisition of… (more)

Subjects/Keywords: Interspersed; reinforcement; extinction

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Coulter, L. E. (2012). The Effects of Increasing Rates of Reinforcement Through an Alternative Fluent Behavior on the Acquisition and Extinction of Behavior in Dogs. (Thesis). University of North Texas. Retrieved from https://digital.library.unt.edu/ark:/67531/metadc149576/

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Coulter, Laura E. “The Effects of Increasing Rates of Reinforcement Through an Alternative Fluent Behavior on the Acquisition and Extinction of Behavior in Dogs.” 2012. Thesis, University of North Texas. Accessed February 25, 2020. https://digital.library.unt.edu/ark:/67531/metadc149576/.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Coulter, Laura E. “The Effects of Increasing Rates of Reinforcement Through an Alternative Fluent Behavior on the Acquisition and Extinction of Behavior in Dogs.” 2012. Web. 25 Feb 2020.

Vancouver:

Coulter LE. The Effects of Increasing Rates of Reinforcement Through an Alternative Fluent Behavior on the Acquisition and Extinction of Behavior in Dogs. [Internet] [Thesis]. University of North Texas; 2012. [cited 2020 Feb 25]. Available from: https://digital.library.unt.edu/ark:/67531/metadc149576/.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Coulter LE. The Effects of Increasing Rates of Reinforcement Through an Alternative Fluent Behavior on the Acquisition and Extinction of Behavior in Dogs. [Thesis]. University of North Texas; 2012. Available from: https://digital.library.unt.edu/ark:/67531/metadc149576/

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of St. Andrews

21. Aquili, Luca. Refinement of biologically inspired models of reinforcement learning .

Degree: 2010, University of St. Andrews

URL: http://hdl.handle.net/10023/886

► Reinforcement learning occurs when organisms adapt the propensities of given behaviours on the basis of associations with reward and punishment. Currently, reinforcement learning models have… (more)

▼ Reinforcement learning occurs when organisms adapt the propensities of given behaviours on the basis of associations with reward and punishment. Currently, reinforcement learning models have been validated in minimalist environments in which only 1-2 environmental stimuli are present as possible predictors of reward. The exception to this is two studies in which the responses of the dopamine system to configurations of multiple stimuli were investigated, however, in both cases the stimuli were presented simultaneously rather than in a sequence. Therefore, we set out to understand how current models of reinforcement learning would respond under more complex conditions in which sequences of events are predictors of reward. In the two experimental chapters of this thesis, we attempted to understand whether midbrain dopaminergic neurons would respond to occasion setters (Chapter 3), and to the overexpectation effect (Chapter 4). In addition, we ran simulations of the behavioural paradigms using temporal difference models of reinforcement learning (Chapter 2) and compared the predictions of the model with the behavioural and neurophysiological data. In Chapter 3, by performing single-neuron recording from VTA and SNpc dopaminergic cells, we demonstrated that our population of neurons were most responsive to the latest predictor of reward, the conditioned stimulus (CS) and not the earliest, the occasion setter (the OS). This is in stark contrast with the predictions of the model (Chapter 2), where the greatest response is seen at the OS onset. We also showed at a neural level that there was only a weak enhancement of the response to the discriminative stimulus (SD) when this was preceded by the OS. On the other hand, at a behavioural level, bar pressing was greatest when the SD was preceded by the OS, demonstrating that rats could use the information provided by the OS, but that dopamine was not controlling the conditioned response. In Chapter 4, our population of dopaminergic neurons showed that they would preferentially respond to only one of the two conditioned stimuli (CSA, CSB) in the overexpectation paradigm. The predictions of the model (Chapter 2) suggested that when the two stimuli would be presented in compound, there would be an inhibitory response if the reward magnitude was kept constant and an excitatory response if the reward magnitude was doubled. The lack of neural firing to one of the two conditioned stimuli, however, does not make for easy interpretation of the data. Perhaps, one of the conditioned stimuli acted as if it were overshadowing the other, resulting in no response to the second CS. Interestingly, at a behavioural level, we did not see increased licking frequency to the compound stimuli presentation, a result that is somewhat at odds with the previous literature. Overall, the results of our experimental chapters suggest that the role that midbrain dopaminergic neurons play in reinforcement learning is more complex than that envisaged by previous… Advisors/Committee Members: Bowman, Eric MacDonald (advisor).

Subjects/Keywords: Dopaminergic; Reinforcement learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Aquili, L. (2010). Refinement of biologically inspired models of reinforcement learning . (Thesis). University of St. Andrews. Retrieved from http://hdl.handle.net/10023/886

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Aquili, Luca. “Refinement of biologically inspired models of reinforcement learning .” 2010. Thesis, University of St. Andrews. Accessed February 25, 2020. http://hdl.handle.net/10023/886.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Aquili, Luca. “Refinement of biologically inspired models of reinforcement learning .” 2010. Web. 25 Feb 2020.

Vancouver:

Aquili L. Refinement of biologically inspired models of reinforcement learning . [Internet] [Thesis]. University of St. Andrews; 2010. [cited 2020 Feb 25]. Available from: http://hdl.handle.net/10023/886.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Aquili L. Refinement of biologically inspired models of reinforcement learning . [Thesis]. University of St. Andrews; 2010. Available from: http://hdl.handle.net/10023/886

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Manitoba

22. Schnerch, Gabriel. Establishing conditioned reinforcers in individuals with developmental disabilities: comparison of the stimulus-stimulus pairing procedure and the discriminative control procedure.

Degree: Psychology, 2014, University of Manitoba

URL: http://hdl.handle.net/1993/30814

► Individuals with developmental disabilities may be sensitive to a limited number of conditioned reinforcers. Therefore, the development of effective procedures to establish conditioned reinforcers in… (more)

Subjects/Keywords: Reinforcement; Pairing; Conditioning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Schnerch, G. (2014). Establishing conditioned reinforcers in individuals with developmental disabilities: comparison of the stimulus-stimulus pairing procedure and the discriminative control procedure. (Thesis). University of Manitoba. Retrieved from http://hdl.handle.net/1993/30814

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Schnerch, Gabriel. “Establishing conditioned reinforcers in individuals with developmental disabilities: comparison of the stimulus-stimulus pairing procedure and the discriminative control procedure.” 2014. Thesis, University of Manitoba. Accessed February 25, 2020. http://hdl.handle.net/1993/30814.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Schnerch, Gabriel. “Establishing conditioned reinforcers in individuals with developmental disabilities: comparison of the stimulus-stimulus pairing procedure and the discriminative control procedure.” 2014. Web. 25 Feb 2020.

Vancouver:

Schnerch G. Establishing conditioned reinforcers in individuals with developmental disabilities: comparison of the stimulus-stimulus pairing procedure and the discriminative control procedure. [Internet] [Thesis]. University of Manitoba; 2014. [cited 2020 Feb 25]. Available from: http://hdl.handle.net/1993/30814.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Schnerch G. Establishing conditioned reinforcers in individuals with developmental disabilities: comparison of the stimulus-stimulus pairing procedure and the discriminative control procedure. [Thesis]. University of Manitoba; 2014. Available from: http://hdl.handle.net/1993/30814

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Northeastern University

23. Flint, Kimberly. A comparison of edible, social, and no contrived reinforcement on the acquisition of a behavior chain.

Degree: MS, Department of Counseling and Applied Educational Psychology, 2011, Northeastern University

URL: http://hdl.handle.net/2047/d20001146

► Reinforcement is used by applied behavior analysts to increase the future frequency of responding. Finding effective reinforcers is important to increase the frequency of behavior.… (more)

Subjects/Keywords: behavioral sciences; comparing reinforcers; contrived reinforcement; reinforcement; Reinforcement (Psychology); Educational psychology; Child Psychology

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Flint, K. (2011). A comparison of edible, social, and no contrived reinforcement on the acquisition of a behavior chain. (Masters Thesis). Northeastern University. Retrieved from http://hdl.handle.net/2047/d20001146

Chicago Manual of Style (16^th Edition):

Flint, Kimberly. “A comparison of edible, social, and no contrived reinforcement on the acquisition of a behavior chain.” 2011. Masters Thesis, Northeastern University. Accessed February 25, 2020. http://hdl.handle.net/2047/d20001146.

MLA Handbook (7^th Edition):

Flint, Kimberly. “A comparison of edible, social, and no contrived reinforcement on the acquisition of a behavior chain.” 2011. Web. 25 Feb 2020.

Vancouver:

Flint K. A comparison of edible, social, and no contrived reinforcement on the acquisition of a behavior chain. [Internet] [Masters thesis]. Northeastern University; 2011. [cited 2020 Feb 25]. Available from: http://hdl.handle.net/2047/d20001146.

Council of Science Editors:

Flint K. A comparison of edible, social, and no contrived reinforcement on the acquisition of a behavior chain. [Masters Thesis]. Northeastern University; 2011. Available from: http://hdl.handle.net/2047/d20001146

The Ohio State University

24. Atnip, Gilbert Wilson. Stimulus-reinforcer and response-reinforcer contingencies in several learning paradigms in the rat.

Degree: PhD, Graduate School, 1975, The Ohio State University

URL: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486993975342509

Subjects/Keywords: Psychology; Reinforcement

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Atnip, G. W. (1975). Stimulus-reinforcer and response-reinforcer contingencies in several learning paradigms in the rat. (Doctoral Dissertation). The Ohio State University. Retrieved from http://rave.ohiolink.edu/etdc/view?acc_num=osu1486993975342509

Chicago Manual of Style (16^th Edition):

Atnip, Gilbert Wilson. “Stimulus-reinforcer and response-reinforcer contingencies in several learning paradigms in the rat.” 1975. Doctoral Dissertation, The Ohio State University. Accessed February 25, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1486993975342509.

MLA Handbook (7^th Edition):

Atnip, Gilbert Wilson. “Stimulus-reinforcer and response-reinforcer contingencies in several learning paradigms in the rat.” 1975. Web. 25 Feb 2020.

Vancouver:

Atnip GW. Stimulus-reinforcer and response-reinforcer contingencies in several learning paradigms in the rat. [Internet] [Doctoral dissertation]. The Ohio State University; 1975. [cited 2020 Feb 25]. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486993975342509.

Council of Science Editors:

Atnip GW. Stimulus-reinforcer and response-reinforcer contingencies in several learning paradigms in the rat. [Doctoral Dissertation]. The Ohio State University; 1975. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486993975342509

The Ohio State University

25. Danson, Carl Merrill. The progressive effects of satiation on simple and complex operant response sequences.

Degree: PhD, Graduate School, 1965, The Ohio State University

URL: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486567559450406

Subjects/Keywords: Psychology; Reinforcement

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Danson, C. M. (1965). The progressive effects of satiation on simple and complex operant response sequences. (Doctoral Dissertation). The Ohio State University. Retrieved from http://rave.ohiolink.edu/etdc/view?acc_num=osu1486567559450406

Chicago Manual of Style (16^th Edition):

Danson, Carl Merrill. “The progressive effects of satiation on simple and complex operant response sequences.” 1965. Doctoral Dissertation, The Ohio State University. Accessed February 25, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1486567559450406.

MLA Handbook (7^th Edition):

Danson, Carl Merrill. “The progressive effects of satiation on simple and complex operant response sequences.” 1965. Web. 25 Feb 2020.

Vancouver:

Danson CM. The progressive effects of satiation on simple and complex operant response sequences. [Internet] [Doctoral dissertation]. The Ohio State University; 1965. [cited 2020 Feb 25]. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486567559450406.

Council of Science Editors:

Danson CM. The progressive effects of satiation on simple and complex operant response sequences. [Doctoral Dissertation]. The Ohio State University; 1965. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486567559450406

The Ohio State University

26. Spence, Norville Edison. The effect of increased fixed interval schedules of reinforcement on the time out behavior of the albino rat in a free operant (two bar) situation.

Degree: PhD, Graduate School, 1968, The Ohio State University

URL: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486647766581908

Subjects/Keywords: Psychology; Reinforcement

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Spence, N. E. (1968). The effect of increased fixed interval schedules of reinforcement on the time out behavior of the albino rat in a free operant (two bar) situation. (Doctoral Dissertation). The Ohio State University. Retrieved from http://rave.ohiolink.edu/etdc/view?acc_num=osu1486647766581908

Chicago Manual of Style (16^th Edition):

Spence, Norville Edison. “The effect of increased fixed interval schedules of reinforcement on the time out behavior of the albino rat in a free operant (two bar) situation.” 1968. Doctoral Dissertation, The Ohio State University. Accessed February 25, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1486647766581908.

MLA Handbook (7^th Edition):

Spence, Norville Edison. “The effect of increased fixed interval schedules of reinforcement on the time out behavior of the albino rat in a free operant (two bar) situation.” 1968. Web. 25 Feb 2020.

Vancouver:

Spence NE. The effect of increased fixed interval schedules of reinforcement on the time out behavior of the albino rat in a free operant (two bar) situation. [Internet] [Doctoral dissertation]. The Ohio State University; 1968. [cited 2020 Feb 25]. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486647766581908.

Council of Science Editors:

Spence NE. The effect of increased fixed interval schedules of reinforcement on the time out behavior of the albino rat in a free operant (two bar) situation. [Doctoral Dissertation]. The Ohio State University; 1968. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486647766581908

The Ohio State University

27. Lesiak, Walter J. The relationships of the internal-external locus of control dimension to scholastic achievement, reflection-impulsivity and residence in priority areas.

Degree: PhD, Graduate School, 1970, The Ohio State University

URL: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486655760439753

Subjects/Keywords: Psychology; Reinforcement

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lesiak, W. J. (1970). The relationships of the internal-external locus of control dimension to scholastic achievement, reflection-impulsivity and residence in priority areas. (Doctoral Dissertation). The Ohio State University. Retrieved from http://rave.ohiolink.edu/etdc/view?acc_num=osu1486655760439753

Chicago Manual of Style (16^th Edition):

Lesiak, Walter J. “The relationships of the internal-external locus of control dimension to scholastic achievement, reflection-impulsivity and residence in priority areas.” 1970. Doctoral Dissertation, The Ohio State University. Accessed February 25, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1486655760439753.

MLA Handbook (7^th Edition):

Lesiak, Walter J. “The relationships of the internal-external locus of control dimension to scholastic achievement, reflection-impulsivity and residence in priority areas.” 1970. Web. 25 Feb 2020.

Vancouver:

Lesiak WJ. The relationships of the internal-external locus of control dimension to scholastic achievement, reflection-impulsivity and residence in priority areas. [Internet] [Doctoral dissertation]. The Ohio State University; 1970. [cited 2020 Feb 25]. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486655760439753.

Council of Science Editors:

Lesiak WJ. The relationships of the internal-external locus of control dimension to scholastic achievement, reflection-impulsivity and residence in priority areas. [Doctoral Dissertation]. The Ohio State University; 1970. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=osu1486655760439753

28. Yunduan, Cui. Practical Model-free Reinforcement Learning in Complex Robot Systems with High Dimensional States : 高次元状態を有する複雑なロボットシステムにおける実用的なモデルフリー強化学習; コウジゲンジョウタイオユウスルフクザツナロボットシステムニオケルジツヨウテキナモデルフリーキョウカガクシュウ.

Degree: 博士(工学), 2017, Nara Institute of Science and Technology / 奈良先端科学技術大学院大学

URL: http://hdl.handle.net/10061/12169

Subjects/Keywords: Reinforcement Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Yunduan, C. (2017). Practical Model-free Reinforcement Learning in Complex Robot Systems with High Dimensional States : 高次元状態を有する複雑なロボットシステムにおける実用的なモデルフリー強化学習; コウジゲンジョウタイオユウスルフクザツナロボットシステムニオケルジツヨウテキナモデルフリーキョウカガクシュウ. (Thesis). Nara Institute of Science and Technology / 奈良先端科学技術大学院大学. Retrieved from http://hdl.handle.net/10061/12169

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Yunduan, Cui. “Practical Model-free Reinforcement Learning in Complex Robot Systems with High Dimensional States : 高次元状態を有する複雑なロボットシステムにおける実用的なモデルフリー強化学習; コウジゲンジョウタイオユウスルフクザツナロボットシステムニオケルジツヨウテキナモデルフリーキョウカガクシュウ.” 2017. Thesis, Nara Institute of Science and Technology / 奈良先端科学技術大学院大学. Accessed February 25, 2020. http://hdl.handle.net/10061/12169.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Yunduan, Cui. “Practical Model-free Reinforcement Learning in Complex Robot Systems with High Dimensional States : 高次元状態を有する複雑なロボットシステムにおける実用的なモデルフリー強化学習; コウジゲンジョウタイオユウスルフクザツナロボットシステムニオケルジツヨウテキナモデルフリーキョウカガクシュウ.” 2017. Web. 25 Feb 2020.

Vancouver:

Yunduan C. Practical Model-free Reinforcement Learning in Complex Robot Systems with High Dimensional States : 高次元状態を有する複雑なロボットシステムにおける実用的なモデルフリー強化学習; コウジゲンジョウタイオユウスルフクザツナロボットシステムニオケルジツヨウテキナモデルフリーキョウカガクシュウ. [Internet] [Thesis]. Nara Institute of Science and Technology / 奈良先端科学技術大学院大学; 2017. [cited 2020 Feb 25]. Available from: http://hdl.handle.net/10061/12169.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Yunduan C. Practical Model-free Reinforcement Learning in Complex Robot Systems with High Dimensional States : 高次元状態を有する複雑なロボットシステムにおける実用的なモデルフリー強化学習; コウジゲンジョウタイオユウスルフクザツナロボットシステムニオケルジツヨウテキナモデルフリーキョウカガクシュウ. [Thesis]. Nara Institute of Science and Technology / 奈良先端科学技術大学院大学; 2017. Available from: http://hdl.handle.net/10061/12169

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Louisiana State University

29. Lark, Catherine Rose. What Motivates Children to Respond? Functional Analysis and Intervention of Math Computation Fluency.

Degree: PhD, Applied Behavior Analysis, 2018, Louisiana State University

URL: https://digitalcommons.lsu.edu/gradschool_dissertations/4579

► An abundance of research exists supporting the use of functional analyses to assess and treat problem behavior. In contrast, little research has been conducted… (more)

Subjects/Keywords: Functional Analysis; Computation Fluency; Reinforcement

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lark, C. R. (2018). What Motivates Children to Respond? Functional Analysis and Intervention of Math Computation Fluency. (Doctoral Dissertation). Louisiana State University. Retrieved from https://digitalcommons.lsu.edu/gradschool_dissertations/4579

Chicago Manual of Style (16^th Edition):

Lark, Catherine Rose. “What Motivates Children to Respond? Functional Analysis and Intervention of Math Computation Fluency.” 2018. Doctoral Dissertation, Louisiana State University. Accessed February 25, 2020. https://digitalcommons.lsu.edu/gradschool_dissertations/4579.

MLA Handbook (7^th Edition):

Lark, Catherine Rose. “What Motivates Children to Respond? Functional Analysis and Intervention of Math Computation Fluency.” 2018. Web. 25 Feb 2020.

Vancouver:

Lark CR. What Motivates Children to Respond? Functional Analysis and Intervention of Math Computation Fluency. [Internet] [Doctoral dissertation]. Louisiana State University; 2018. [cited 2020 Feb 25]. Available from: https://digitalcommons.lsu.edu/gradschool_dissertations/4579.

Council of Science Editors:

Lark CR. What Motivates Children to Respond? Functional Analysis and Intervention of Math Computation Fluency. [Doctoral Dissertation]. Louisiana State University; 2018. Available from: https://digitalcommons.lsu.edu/gradschool_dissertations/4579

University of Alberta

30. Dick, Travis B. Policy Gradient Reinforcement Learning Without Regret.

Degree: MS, Department of Computing Science, 2015, University of Alberta

URL: https://era.library.ualberta.ca/files/df65vb663

► This thesis consists of two independent projects, each contributing to a central goal of artificial intelligence research: to build computer systems that are capable of… (more)

▼ This thesis consists of two independent projects, each contributing to a central goal of artificial intelligence research: to build computer systems that are capable of performing tasks and solving problems without problem-specific direction from us, their designers. I focus on two formal learning problems that have a strong mathematical grounding. Many real-world learning problems can be cast as instances of one of these two problems. Whenever our translation from the real to the formal accurately captures the character of the problem, then the mathematical arguments we make about algorithms in the formal setting will approximately hold in the real-world as well. The first project focuses on an open question in the theory of policy gradient reinforcement learning methods. These methods learn by trial and error and decide whether a trial was good or bad by comparing its outcome to a given baseline. The baseline has no impact on the formal asymptotic guarantees for policy gradient methods, but it does alter their finite-time behaviour. This immediately raises the question: which baseline should we use? I propose that the baseline should be chosen such that a certain estimate used internally by policy gradient methods has the smallest error. I prove that, under slightly idealistic assumptions, this baseline gives a good upper bound on the regret of policy gradient methods. I derive closed-form expressions for this baseline in terms of properties of the formal learning problem and the computer's behaviour. The quantities appearing in the closed form expressions are often unknown, so I also propose two algorithms for estimating this baseline from only known quantities. Finally, I present an empirical comparison of commonly used baselines that demonstrates improved performance when using my proposed baseline. The second project focuses on a recently proposed class of formal learning problems that is in the intersection of two fields of computing science research: reinforcement learning and online learning. The considered problems are sometimes called online Markov decision processes, or Markov decision processes with changing rewards. The unique property of this class is that it assumes the computer's environment is adversarial, as though it were playing a game against the computer. This is in contrast to the more common assumption that the environment's behaviour is determined entirely by stochastic models. I propose three new algorithms for learning in Markov decision processes with changing rewards under various conditions. I prove theoretical performance guarantees for each algorithm that either complement or improve the best existing results and that often hold even under weaker assumptions. This comes at the cost of increased (but still polynomial) computational complexity. Finally, in the development and analysis of these algorithms, it was necessary to analyze an approximate version of a well-known optimization algorithm called online mirror ascent. To the best of my knowledge, this is the first rigorous analysis…

Subjects/Keywords: Policy Gradient; Baseline; Reinforcement Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Dick, T. B. (2015). Policy Gradient Reinforcement Learning Without Regret. (Masters Thesis). University of Alberta. Retrieved from https://era.library.ualberta.ca/files/df65vb663

Chicago Manual of Style (16^th Edition):

Dick, Travis B. “Policy Gradient Reinforcement Learning Without Regret.” 2015. Masters Thesis, University of Alberta. Accessed February 25, 2020. https://era.library.ualberta.ca/files/df65vb663.

MLA Handbook (7^th Edition):

Dick, Travis B. “Policy Gradient Reinforcement Learning Without Regret.” 2015. Web. 25 Feb 2020.

Vancouver:

Dick TB. Policy Gradient Reinforcement Learning Without Regret. [Internet] [Masters thesis]. University of Alberta; 2015. [cited 2020 Feb 25]. Available from: https://era.library.ualberta.ca/files/df65vb663.

Council of Science Editors:

Dick TB. Policy Gradient Reinforcement Learning Without Regret. [Masters Thesis]. University of Alberta; 2015. Available from: https://era.library.ualberta.ca/files/df65vb663

		in
And / Or
		in
And / Or
		in
And / Or
		in

Open Access Theses and Dissertations