subject:(Modular inverse reinforcement learning)

University of Texas – Austin

1. -8073-3276. Parameterized modular inverse reinforcement learning.

Degree: MSin Computer Sciences, Computer Science, 2015, University of Texas – Austin

► Reinforcement learning and inverse reinforcement learning can be used to model and understand human behaviors. However, due to the curse of dimensionality, their use as… (more)

Subjects/Keywords: Reinforcement learning; Artificial intelligence; Inverse reinforcement learning; Modular inverse reinforcement learning; Reinforcement learning algorithms; Human navigation behaviors

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

-8073-3276. (2015). Parameterized modular inverse reinforcement learning. (Masters Thesis). University of Texas – Austin. Retrieved from http://hdl.handle.net/2152/46987

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Chicago Manual of Style (16^th Edition):

-8073-3276. “Parameterized modular inverse reinforcement learning.” 2015. Masters Thesis, University of Texas – Austin. Accessed December 15, 2019. http://hdl.handle.net/2152/46987.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

MLA Handbook (7^th Edition):

-8073-3276. “Parameterized modular inverse reinforcement learning.” 2015. Web. 15 Dec 2019.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Vancouver:

-8073-3276. Parameterized modular inverse reinforcement learning. [Internet] [Masters thesis]. University of Texas – Austin; 2015. [cited 2019 Dec 15]. Available from: http://hdl.handle.net/2152/46987.

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Council of Science Editors:

-8073-3276. Parameterized modular inverse reinforcement learning. [Masters Thesis]. University of Texas – Austin; 2015. Available from: http://hdl.handle.net/2152/46987

Note: this citation may be lacking information needed for this citation format:
Author name may be incomplete

Rice University

2. Daptardar, Saurabh. The Science of Mind Reading: New Inverse Optimal Control Framework.

Degree: MS, Engineering, 2018, Rice University

URL: http://hdl.handle.net/1911/105893

► Continuous control and planning by the brain remain poorly understood and is a major challenge in the field of Neuroscience. To truly say that we… (more)

Subjects/Keywords: Inverse Reinforcement Learning; Inverse Optimal Control; Reinforcement Learning; Optimal Control; Neuroscience

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Daptardar, S. (2018). The Science of Mind Reading: New Inverse Optimal Control Framework. (Masters Thesis). Rice University. Retrieved from http://hdl.handle.net/1911/105893

Chicago Manual of Style (16^th Edition):

Daptardar, Saurabh. “The Science of Mind Reading: New Inverse Optimal Control Framework.” 2018. Masters Thesis, Rice University. Accessed December 15, 2019. http://hdl.handle.net/1911/105893.

MLA Handbook (7^th Edition):

Daptardar, Saurabh. “The Science of Mind Reading: New Inverse Optimal Control Framework.” 2018. Web. 15 Dec 2019.

Vancouver:

Daptardar S. The Science of Mind Reading: New Inverse Optimal Control Framework. [Internet] [Masters thesis]. Rice University; 2018. [cited 2019 Dec 15]. Available from: http://hdl.handle.net/1911/105893.

Council of Science Editors:

Daptardar S. The Science of Mind Reading: New Inverse Optimal Control Framework. [Masters Thesis]. Rice University; 2018. Available from: http://hdl.handle.net/1911/105893

NSYSU

3. Tseng, Yi-Chia. An Unified Approach to Inverse Reinforcement Learning by Oppositive Demonstrations.

Degree: Master, Electrical Engineering, 2015, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727115-130716

► Reinforcement learning (RL) techniques use a reward function to correct a learning agent to solve sequential decision making problems through interactions with a dynamic environment,… (more)

Subjects/Keywords: Apprenticeship Learning; Feature weight; Inverse Reinforcement learning; Reward function; Reinforcement learning

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Tseng, Y. (2015). An Unified Approach to Inverse Reinforcement Learning by Oppositive Demonstrations. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727115-130716

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):

Tseng, Yi-Chia. “An Unified Approach to Inverse Reinforcement Learning by Oppositive Demonstrations.” 2015. Thesis, NSYSU. Accessed December 15, 2019. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727115-130716.

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

MLA Handbook (7^th Edition):

Tseng, Yi-Chia. “An Unified Approach to Inverse Reinforcement Learning by Oppositive Demonstrations.” 2015. Web. 15 Dec 2019.

Vancouver:

Tseng Y. An Unified Approach to Inverse Reinforcement Learning by Oppositive Demonstrations. [Internet] [Thesis]. NSYSU; 2015. [cited 2019 Dec 15]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727115-130716.

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

Council of Science Editors:

Tseng Y. An Unified Approach to Inverse Reinforcement Learning by Oppositive Demonstrations. [Thesis]. NSYSU; 2015. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0727115-130716

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

NSYSU

4. Lin, Hung-shyuan. Applying The Concept of Fuzzy Logic to Inverse Reinforcement Learning.

Degree: Master, Electrical Engineering, 2015, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1025115-185021

► Itâs a study on Reinforcement Learning, learning interaction of agents and dynamic environment to get reward function R, and update the policy, converge learning and… (more)

Subjects/Keywords: Inverse reinforcement learning; Reward function; Fuzzy; Reinforcement learning; AdaBoost; Apprenticeship learning

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Lin, H. (2015). Applying The Concept of Fuzzy Logic to Inverse Reinforcement Learning. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1025115-185021

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):

Lin, Hung-shyuan. “Applying The Concept of Fuzzy Logic to Inverse Reinforcement Learning.” 2015. Thesis, NSYSU. Accessed December 15, 2019. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1025115-185021.

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

MLA Handbook (7^th Edition):

Lin, Hung-shyuan. “Applying The Concept of Fuzzy Logic to Inverse Reinforcement Learning.” 2015. Web. 15 Dec 2019.

Vancouver:

Lin H. Applying The Concept of Fuzzy Logic to Inverse Reinforcement Learning. [Internet] [Thesis]. NSYSU; 2015. [cited 2019 Dec 15]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1025115-185021.

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

Council of Science Editors:

Lin H. Applying The Concept of Fuzzy Logic to Inverse Reinforcement Learning. [Thesis]. NSYSU; 2015. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1025115-185021

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

University of Illinois – Chicago

5. Tirinzoni, Andrea. Adversarial Inverse Reinforcement Learning with Changing Dynamics.

Degree: 2017, University of Illinois – Chicago

URL: http://hdl.handle.net/10027/22081

► Most work on inverse reinforcement learning, the problem of recovering the unknown reward function being optimized by a decision-making agent, has focused on cases where… (more)

Subjects/Keywords: Machine Learning; Inverse Reinforcement Learning; Reinforcement Learning; Adversarial Prediction; Markov Decision Process; Imitation Learning

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Tirinzoni, A. (2017). Adversarial Inverse Reinforcement Learning with Changing Dynamics. (Thesis). University of Illinois – Chicago. Retrieved from http://hdl.handle.net/10027/22081

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):

Tirinzoni, Andrea. “Adversarial Inverse Reinforcement Learning with Changing Dynamics.” 2017. Thesis, University of Illinois – Chicago. Accessed December 15, 2019. http://hdl.handle.net/10027/22081.

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

MLA Handbook (7^th Edition):

Tirinzoni, Andrea. “Adversarial Inverse Reinforcement Learning with Changing Dynamics.” 2017. Web. 15 Dec 2019.

Vancouver:

Tirinzoni A. Adversarial Inverse Reinforcement Learning with Changing Dynamics. [Internet] [Thesis]. University of Illinois – Chicago; 2017. [cited 2019 Dec 15]. Available from: http://hdl.handle.net/10027/22081.

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

Council of Science Editors:

Tirinzoni A. Adversarial Inverse Reinforcement Learning with Changing Dynamics. [Thesis]. University of Illinois – Chicago; 2017. Available from: http://hdl.handle.net/10027/22081

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

University of Illinois – Chicago

6. Chen, Xiangli. Robust Structured Prediction for Process Data.

Degree: 2017, University of Illinois – Chicago

URL: http://hdl.handle.net/10027/21987

► Processes involve a series of actions performed to achieve a particular result. Developing prediction models for process data is important for many real problems such… (more)

Subjects/Keywords: Structured Prediction; Optimal Control; Reinforcement Learning; Inverse Reinforcement Learning; Imitation Learning; Regression; Covariate Shift

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Chen, X. (2017). Robust Structured Prediction for Process Data. (Thesis). University of Illinois – Chicago. Retrieved from http://hdl.handle.net/10027/21987

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):

Chen, Xiangli. “Robust Structured Prediction for Process Data.” 2017. Thesis, University of Illinois – Chicago. Accessed December 15, 2019. http://hdl.handle.net/10027/21987.

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

MLA Handbook (7^th Edition):

Chen, Xiangli. “Robust Structured Prediction for Process Data.” 2017. Web. 15 Dec 2019.

Vancouver:

Chen X. Robust Structured Prediction for Process Data. [Internet] [Thesis]. University of Illinois – Chicago; 2017. [cited 2019 Dec 15]. Available from: http://hdl.handle.net/10027/21987.

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

Council of Science Editors:

Chen X. Robust Structured Prediction for Process Data. [Thesis]. University of Illinois – Chicago; 2017. Available from: http://hdl.handle.net/10027/21987

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

NSYSU

7. Cheng, Tien-yu. Inverse Reinforcement Learning based on Critical State.

Degree: Master, Electrical Engineering, 2014, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1028114-170500

► Reinforcement Learning (RL) makes an agent learn through interacting with a dynamic environment. One fundamental assumption of existing RL algorithms is that reward function, the… (more)

Subjects/Keywords: reward feature construction; Apprenticeship Learning; Inverse Reinforcement learning; reward function; Reinforcement learning

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Cheng, T. (2014). Inverse Reinforcement Learning based on Critical State. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1028114-170500

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):

Cheng, Tien-yu. “Inverse Reinforcement Learning based on Critical State.” 2014. Thesis, NSYSU. Accessed December 15, 2019. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1028114-170500.

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

MLA Handbook (7^th Edition):

Cheng, Tien-yu. “Inverse Reinforcement Learning based on Critical State.” 2014. Web. 15 Dec 2019.

Vancouver:

Cheng T. Inverse Reinforcement Learning based on Critical State. [Internet] [Thesis]. NSYSU; 2014. [cited 2019 Dec 15]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1028114-170500.

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

Council of Science Editors:

Cheng T. Inverse Reinforcement Learning based on Critical State. [Thesis]. NSYSU; 2014. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-1028114-170500

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

University of Southern California

8. Kalakrishnan, Mrinal. Learning objective functions for autonomous motion generation.

Degree: PhD, Computer Science, 2014, University of Southern California

URL: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/369146/rec/3781

► Planning and optimization methods have been widely applied to the problem of trajectory generation for autonomous robotics. The performance of such methods, however, is critically… (more)

▼ Planning and optimization methods have been widely applied to the problem of trajectory generation for autonomous robotics. The performance of such methods, however, is critically dependent on the choice of objective function being optimized, and is non‐trivial to design. On the other end of the spectrum, efforts on learning autonomous behavior from user‐provided demonstrations have largely been focused on reproducing behavior similar in appearance to the provided demonstrations. An alternative approach, known as Inverse Reinforcement Learning (IRL), is to learn an objective function that the demonstrations are assumed to be optimal under. With the help of a planner or trajectory optimizer, such an approach allows the system to synthesize novel behavior in situations that were not experienced in the demonstrations. ❧ We present novel algorithms for IRL that have successfully been applied in two real‐world, competitive robotics settings: (1) In the domain of rough terrain quadruped locomotion, we present an algorithm that learns an objective function for foothold selection based on ”terrain templates”. The learner automatically generates and selects the appropriate features which form the objective function, which reduces the need for feature engineering while attaining a high level of generalization. (2) For the domain of autonomous manipulation, we present a probabilistic model of optimal trajectories, which results in new algorithms for inverse reinforcement learning and trajectory optimization in high‐dimensional settings. We apply this method to two problems in robotic manipulation: redundancy resolution in inverse kinematics, and trajectory optimization for grasping and manipulation. Both methods have proven themselves as part of larger integrated systems in competitive settings against other teams, where testing was conducted by an independent test team in situations that were not seen during training. Advisors/Committee Members: Schaal, Stefan (Committee Chair), Sukhatme, Gaurav S. (Committee Member), Valero-Cuevas, Francisco (Committee Member).

Subjects/Keywords: robotics; machine learning; motion planning; trajectory optimization; inverse reinforcement learning; reinforcement learning; locomotion; manipulation

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Kalakrishnan, M. (2014). Learning objective functions for autonomous motion generation. (Doctoral Dissertation). University of Southern California. Retrieved from http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/369146/rec/3781

Chicago Manual of Style (16^th Edition):

Kalakrishnan, Mrinal. “Learning objective functions for autonomous motion generation.” 2014. Doctoral Dissertation, University of Southern California. Accessed December 15, 2019. http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/369146/rec/3781.

MLA Handbook (7^th Edition):

Kalakrishnan, Mrinal. “Learning objective functions for autonomous motion generation.” 2014. Web. 15 Dec 2019.

Vancouver:

Kalakrishnan M. Learning objective functions for autonomous motion generation. [Internet] [Doctoral dissertation]. University of Southern California; 2014. [cited 2019 Dec 15]. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/369146/rec/3781.

Council of Science Editors:

Kalakrishnan M. Learning objective functions for autonomous motion generation. [Doctoral Dissertation]. University of Southern California; 2014. Available from: http://digitallibrary.usc.edu/cdm/compoundobject/collection/p15799coll3/id/369146/rec/3781

University of New South Wales

9. Nguyen, Hung. Apprenticeship Bootstrapping: Multi-Skill Reinforcement Learning for Autonomous Unmanned Aerial Vehicles.

Degree: Engineering & Information Technology, 2018, University of New South Wales

URL: http://handle.unsw.edu.au/1959.4/60412 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:52104/SOURCE02?view=true

► Apprenticeship Learning (AL) uses data collected from humans on tasks to design machine-learning algorithms to imitate the skills used by humans. Such a powerful approach… (more)

▼ Apprenticeship Learning (AL) uses data collected from humans on tasks to design machine-learning algorithms to imitate the skills used by humans. Such a powerful approach to developing autonomous machines comes with challenges stemming from its reliance on the existence of expert humans who can perform the task and their willingness to be available. In this thesis, Apprenticeship Bootstrapping (ABS) is proposed as a new learning algorithm that relies on humans who are experts on less-complex tasks to aggregate the skills required for more complex ones. ABS has been validated using a ground and aerial coordination task (GACT), where an unmanned aerial vehicle (UAV) needs to autonomously follow a group of unmanned ground vehicles (UGVs) while maintaining the group within the field of view of the UAV's camera.ABS decomposes the complex control task for the UAV operator into simpler sub-tasks which an operator is available to perform and to collect demonstrations from. Two proposed learning approaches, apprenticeship bootstrapping via deep learning and inverse reinforcement learning (ABS-DL and ABS-IRL, respectively), are used to address this challenge. In ABS-DL, deep learning, which has shown dramatic advances in terms of effectively work on raw data, is attractive for learning directly from demonstrations of sub-tasks. However, it may not be effective for acquiring a desirable policy, as it relies heavily on the quality of demonstrations. The quality of demonstrations may not be good because of errors in collecting expert demonstrations caused by the limitations of the techniques, or poor demonstrations caused by the expert. ABS-IRL addresses these issues by recovering the expert reward function from demonstrations on the sub-tasks. In ABS-IRL, during every learning episode, the learner acts learned policy and re-optimizes its learned model while performing the task. This learning approach allows the leaner to avoid learning incorrect or poor demonstrations.Both ABS-DL and ABS-IRL were tested on GACT and results confirmed that ABS-IRL could bootstrap the more complex skill from lower less-complex ones. Advisors/Committee Members: Abbass, Hussein, Engineering & Information Technology, UNSW Canberra, UNSW, Garratt, Mathew, Engineering & Information Technology, UNSW Canberra, UNSW, Bui, Lam, Le Quy Don - Viet nam.

Subjects/Keywords: Apprenticeship Learning; Reinforcement learning; Inverse Reinforcement Learning; Apprenticeship Boostrapping; UAV and UGVs

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Nguyen, H. (2018). Apprenticeship Bootstrapping: Multi-Skill Reinforcement Learning for Autonomous Unmanned Aerial Vehicles. (Masters Thesis). University of New South Wales. Retrieved from http://handle.unsw.edu.au/1959.4/60412 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:52104/SOURCE02?view=true

Chicago Manual of Style (16^th Edition):

Nguyen, Hung. “Apprenticeship Bootstrapping: Multi-Skill Reinforcement Learning for Autonomous Unmanned Aerial Vehicles.” 2018. Masters Thesis, University of New South Wales. Accessed December 15, 2019. http://handle.unsw.edu.au/1959.4/60412 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:52104/SOURCE02?view=true.

MLA Handbook (7^th Edition):

Nguyen, Hung. “Apprenticeship Bootstrapping: Multi-Skill Reinforcement Learning for Autonomous Unmanned Aerial Vehicles.” 2018. Web. 15 Dec 2019.

Vancouver:

Nguyen H. Apprenticeship Bootstrapping: Multi-Skill Reinforcement Learning for Autonomous Unmanned Aerial Vehicles. [Internet] [Masters thesis]. University of New South Wales; 2018. [cited 2019 Dec 15]. Available from: http://handle.unsw.edu.au/1959.4/60412 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:52104/SOURCE02?view=true.

Council of Science Editors:

Nguyen H. Apprenticeship Bootstrapping: Multi-Skill Reinforcement Learning for Autonomous Unmanned Aerial Vehicles. [Masters Thesis]. University of New South Wales; 2018. Available from: http://handle.unsw.edu.au/1959.4/60412 ; https://unsworks.unsw.edu.au/fapi/datastream/unsworks:52104/SOURCE02?view=true

NSYSU

10. Chiang, Hsuan-yi. Action Segmentation and Learning by Inverse Reinforcement Learning.

Degree: Master, Electrical Engineering, 2015, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0906115-151230

► Reinforcement learning allows agents to learn behaviors through trial and error. However, as the level of difficulty increases, the reward function of the mission also… (more)

Subjects/Keywords: Upper Confidence Bounds; Adaboost classifier; reward function; Inverse 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):

Chiang, H. (2015). Action Segmentation and Learning by Inverse Reinforcement Learning. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0906115-151230

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):

Chiang, Hsuan-yi. “Action Segmentation and Learning by Inverse Reinforcement Learning.” 2015. Thesis, NSYSU. Accessed December 15, 2019. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0906115-151230.

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

MLA Handbook (7^th Edition):

Chiang, Hsuan-yi. “Action Segmentation and Learning by Inverse Reinforcement Learning.” 2015. Web. 15 Dec 2019.

Vancouver:

Chiang H. Action Segmentation and Learning by Inverse Reinforcement Learning. [Internet] [Thesis]. NSYSU; 2015. [cited 2019 Dec 15]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0906115-151230.

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

Council of Science Editors:

Chiang H. Action Segmentation and Learning by Inverse Reinforcement Learning. [Thesis]. NSYSU; 2015. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0906115-151230

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

11. Das, Indrajit. Inverse reinforcement learning of risk-sensitive utility.

Degree: MS, Computer Science, 2016, University of Georgia

URL: http://purl.galileo.usg.edu/uga_etd/das_indrajit_201608_ms

► The uncertain and stochastic nature of the real world poses a challenge for autonomous cars in making decisions to ensure appropriate motion, considering the safety… (more)

Subjects/Keywords: Inverse Reinforcement Learning

…9 2.3 Inverse Reinforcement Learning… …decision makers using cumulative rewards. We apply Inverse Reinforcement Learning (IRL)… …decision making in self-driving cars. 2 We have developed an Inverse Reinforcement Learning (… …function. 3 We are validating the Inverse Reinforcement Learning algorithm with the help of a… …Theory and Inverse Reinforcement Learning, which are the building blocks of both the problem…

9 more images…

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Das, I. (2016). Inverse reinforcement learning of risk-sensitive utility. (Masters Thesis). University of Georgia. Retrieved from http://purl.galileo.usg.edu/uga_etd/das_indrajit_201608_ms

Chicago Manual of Style (16^th Edition):

Das, Indrajit. “Inverse reinforcement learning of risk-sensitive utility.” 2016. Masters Thesis, University of Georgia. Accessed December 15, 2019. http://purl.galileo.usg.edu/uga_etd/das_indrajit_201608_ms.

MLA Handbook (7^th Edition):

Das, Indrajit. “Inverse reinforcement learning of risk-sensitive utility.” 2016. Web. 15 Dec 2019.

Vancouver:

Das I. Inverse reinforcement learning of risk-sensitive utility. [Internet] [Masters thesis]. University of Georgia; 2016. [cited 2019 Dec 15]. Available from: http://purl.galileo.usg.edu/uga_etd/das_indrajit_201608_ms.

Council of Science Editors:

Das I. Inverse reinforcement learning of risk-sensitive utility. [Masters Thesis]. University of Georgia; 2016. Available from: http://purl.galileo.usg.edu/uga_etd/das_indrajit_201608_ms

12. Trivedi, Maulesh. Inverse learning of robot behavior for ad-hoc teamwork.

Degree: MS, Artificial Intelligence, 2016, University of Georgia

URL: http://purl.galileo.usg.edu/uga_etd/trivedi_maulesh_201608_ms

► Machine Learning and Robotics present a very intriguing combination of research in Artificial Intelligence. Inverse Reinforcement Learning (IRL) algorithms have generated a great deal of… (more)

Subjects/Keywords: Inverse Reinforcement Learning

…Motivation for Inverse Reinforcement Learning Now that we have described a way of modelling… …6 Thus, our research addresses the problem of Inverse Reinforcement Learning (IRL… …conventional reinforcement learning techniques become mute in these situations. Inverse Reinforcement… …have not been developed to work with multi-agent inverse reinforcement learning domains… …task [18] [20] but do not use the inverse 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):

Trivedi, M. (2016). Inverse learning of robot behavior for ad-hoc teamwork. (Masters Thesis). University of Georgia. Retrieved from http://purl.galileo.usg.edu/uga_etd/trivedi_maulesh_201608_ms

Chicago Manual of Style (16^th Edition):

Trivedi, Maulesh. “Inverse learning of robot behavior for ad-hoc teamwork.” 2016. Masters Thesis, University of Georgia. Accessed December 15, 2019. http://purl.galileo.usg.edu/uga_etd/trivedi_maulesh_201608_ms.

MLA Handbook (7^th Edition):

Trivedi, Maulesh. “Inverse learning of robot behavior for ad-hoc teamwork.” 2016. Web. 15 Dec 2019.

Vancouver:

Trivedi M. Inverse learning of robot behavior for ad-hoc teamwork. [Internet] [Masters thesis]. University of Georgia; 2016. [cited 2019 Dec 15]. Available from: http://purl.galileo.usg.edu/uga_etd/trivedi_maulesh_201608_ms.

Council of Science Editors:

Trivedi M. Inverse learning of robot behavior for ad-hoc teamwork. [Masters Thesis]. University of Georgia; 2016. Available from: http://purl.galileo.usg.edu/uga_etd/trivedi_maulesh_201608_ms

13. Paraskevopoulos, Vasileios. Design of optimal neural network control strategies with minimal a priori knowledge.

Degree: PhD, 2000, University of Sussex

URL: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.324189

Subjects/Keywords: 629.8; Reinforcement learning; Real time; Modular

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Paraskevopoulos, V. (2000). Design of optimal neural network control strategies with minimal a priori knowledge. (Doctoral Dissertation). University of Sussex. Retrieved from https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.324189

Chicago Manual of Style (16^th Edition):

Paraskevopoulos, Vasileios. “Design of optimal neural network control strategies with minimal a priori knowledge.” 2000. Doctoral Dissertation, University of Sussex. Accessed December 15, 2019. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.324189.

MLA Handbook (7^th Edition):

Paraskevopoulos, Vasileios. “Design of optimal neural network control strategies with minimal a priori knowledge.” 2000. Web. 15 Dec 2019.

Vancouver:

Paraskevopoulos V. Design of optimal neural network control strategies with minimal a priori knowledge. [Internet] [Doctoral dissertation]. University of Sussex; 2000. [cited 2019 Dec 15]. Available from: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.324189.

Council of Science Editors:

Paraskevopoulos V. Design of optimal neural network control strategies with minimal a priori knowledge. [Doctoral Dissertation]. University of Sussex; 2000. Available from: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.324189

NSYSU

14. Chen, Yan-heng. Analysis of Another Left Shift Binary GCD Algorithm.

Degree: Master, Computer Science and Engineering, 2009, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0714109-121741

► In general, to compute the modular inverse is very important in information security, many encrypt/decrypt and signature algorithms always need to use it. In 2007,… (more)

Subjects/Keywords: Self-test; Modular inverse; GCD

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Chen, Y. (2009). Analysis of Another Left Shift Binary GCD Algorithm. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0714109-121741

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):

Chen, Yan-heng. “Analysis of Another Left Shift Binary GCD Algorithm.” 2009. Thesis, NSYSU. Accessed December 15, 2019. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0714109-121741.

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

MLA Handbook (7^th Edition):

Chen, Yan-heng. “Analysis of Another Left Shift Binary GCD Algorithm.” 2009. Web. 15 Dec 2019.

Vancouver:

Chen Y. Analysis of Another Left Shift Binary GCD Algorithm. [Internet] [Thesis]. NSYSU; 2009. [cited 2019 Dec 15]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0714109-121741.

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

Council of Science Editors:

Chen Y. Analysis of Another Left Shift Binary GCD Algorithm. [Thesis]. NSYSU; 2009. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0714109-121741

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

University of Oxford

15. Wulfmeier, Markus. Efficient supervision for robot learning via imitation, simulation, and adaptation.

Degree: PhD, 2018, University of Oxford

URL: http://ora.ox.ac.uk/objects/uuid:2b5eeb55-639a-40ae-83b7-bd01fc8fd6cc ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.757819

► In order to enable more widespread application of robots, we are required to reduce the human effort for the introduction of existing robotic platforms to… (more)

▼ In order to enable more widespread application of robots, we are required to reduce the human effort for the introduction of existing robotic platforms to new environments and tasks. In this thesis, we identify three complementary strategies to address this challenge, via the use of imitation learning, domain adaptation, and transfer learning based on simulations. The overall work strives to reduce the effort of generating training data by employing inexpensively obtainable labels and by transferring information between different domains with deviating underlying properties. Imitation learning enables a straightforward way for untrained personnel to teach robots to perform tasks by providing demonstrations, which represent a comparably inexpensive source of supervision. We develop a scalable approach to identify the preferences underlying demonstration data via the framework of inverse reinforcement learning. The method enables integration of the extracted preferences as cost maps into existing motion planning systems. We further incorporate prior domain knowledge and demonstrate that the approach outperforms the baselines including manually crafted cost functions. In addition to employing low-cost labels from demonstration, we investigate the adaptation of models to domains without available supervisory information. Specifically, the challenge of appearance changes in outdoor robotics such as illumination and weather shifts is addressed using an adversarial domain adaptation approach. A principal advantage of the method over prior work is the straightforwardness of adapting arbitrary, state-of-the-art neural network architectures. Finally, we demonstrate performance benefits of the method for semantic segmentation of drivable terrain. Our last contribution focuses on simulation to real world transfer learning, where the characteristic differences are not only regarding the visual appearance but the underlying system dynamics. Our work aims at parallel training in both systems and mutual guidance via auxiliary alignment rewards to accelerate training for real world systems. The approach is shown to outperform various baselines as well as a unilateral alignment variant.

Subjects/Keywords: Machine learning; Robotics; Domain Adaptation; Imitation Learning; Inverse Reinforcement Learning; Mobile Robotics; Transfer Learning; Autonomous Driving

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Wulfmeier, M. (2018). Efficient supervision for robot learning via imitation, simulation, and adaptation. (Doctoral Dissertation). University of Oxford. Retrieved from http://ora.ox.ac.uk/objects/uuid:2b5eeb55-639a-40ae-83b7-bd01fc8fd6cc ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.757819

Chicago Manual of Style (16^th Edition):

Wulfmeier, Markus. “Efficient supervision for robot learning via imitation, simulation, and adaptation.” 2018. Doctoral Dissertation, University of Oxford. Accessed December 15, 2019. http://ora.ox.ac.uk/objects/uuid:2b5eeb55-639a-40ae-83b7-bd01fc8fd6cc ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.757819.

MLA Handbook (7^th Edition):

Wulfmeier, Markus. “Efficient supervision for robot learning via imitation, simulation, and adaptation.” 2018. Web. 15 Dec 2019.

Vancouver:

Wulfmeier M. Efficient supervision for robot learning via imitation, simulation, and adaptation. [Internet] [Doctoral dissertation]. University of Oxford; 2018. [cited 2019 Dec 15]. Available from: http://ora.ox.ac.uk/objects/uuid:2b5eeb55-639a-40ae-83b7-bd01fc8fd6cc ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.757819.

Council of Science Editors:

Wulfmeier M. Efficient supervision for robot learning via imitation, simulation, and adaptation. [Doctoral Dissertation]. University of Oxford; 2018. Available from: http://ora.ox.ac.uk/objects/uuid:2b5eeb55-639a-40ae-83b7-bd01fc8fd6cc ; https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.757819

16. Chandramohan, Senthilkumar. Revisiting user simulation in dialogue systems : do we still need them ? : will imitation play the role of simulation ? : Revisiter la simulation d'utilisateurs dans les systèmes de dialogue parlé : est-elle encore nécessaire ? : est-ce que l'imitation peut jouer le rôle de la simulation ?.

Degree: Docteur es, Informatique, 2012, Avignon

URL: http://www.theses.fr/2012AVIG0185

►

Les récents progrès dans le domaine du traitement du langage ont apporté un intérêt significatif à la mise en oeuvre de systèmes de dialogue parlé.… (more)

▼

Les récents progrès dans le domaine du traitement du langage ont apporté un intérêt significatif à la mise en oeuvre de systèmes de dialogue parlé. Ces derniers sont des interfaces utilisant le langage naturel comme medium d'interaction entre le système et l'utilisateur. Le module de gestion de dialogue choisit le moment auquel l'information qu'il choisit doit être échangée avec l'utilisateur. Ces dernières années, l'optimisation de dialogue parlé en utilisant l'apprentissage par renforcement est devenue la référence. Cependant, une grande partie des algorithmes utilisés nécessite une importante quantité de données pour être efficace. Pour gérer ce problème, des simulations d'utilisateurs ont été introduites. Cependant, ces modèles introduisent des erreurs. Par un choix judicieux d'algorithmes, la quantité de données d'entraînement peut être réduite et ainsi la modélisation de l'utilisateur évitée. Ces travaux concernent une partie des contributions présentées. L'autre partie des travaux consiste à proposer une modélisation à partir de données réelles des utilisateurs au moyen de l'apprentissage par renforcement inverse

Recent advancements in the area of spoken language processing and the wide acceptance of portable devices, have attracted signicant interest in spoken dialogue systems.These conversational systems are man-machine interfaces which use natural language (speech) as the medium of interaction.In order to conduct dialogues, computers must have the ability to decide when and what information has to be exchanged with the users. The dialogue management module is responsible to make these decisions so that the intended task (such as ticket booking or appointment scheduling) can be achieved.Thus learning a good strategy for dialogue management is a critical task.In recent years reinforcement learning-based dialogue management optimization has evolved to be the state-of-the-art. A majority of the algorithms used for this purpose needs vast amounts of training data.However, data generation in the dialogue domain is an expensive and time consuming process. In order to cope with this and also to evaluatethe learnt dialogue strategies, user modelling in dialogue systems was introduced. These models simulate real users in order to generate synthetic data.Being computational models, they introduce some degree of modelling errors. In spite of this, system designers are forced to employ user models due to the data requirement of conventional reinforcement learning algorithms can learn optimal dialogue strategies from limited amount of training data when compared to the conventional algorithms. As a consequence of this, user models are no longer required for the purpose of optimization, yet they continue to provide a fast and easy means for quantifying the quality of dialogue strategies. Since existing methods for user modelling are relatively less realistic compared to real user behaviors, the focus is shifted towards user modelling by means of inverse reinforcement learning. Using experimental results, the proposed…

Advisors/Committee Members: Lefèvre, Fabrice (thesis director), Pietquin, Olivier (thesis director).

Subjects/Keywords: Simulation d'utilisateurs; Systèmes de dialogue parlé; Apprentissage par renforcement; Apprentissage par renforcement inverse; Gestion de dialogue; User simulation; Spoken dialogue systems; Reinforcement learning; Inverse reinforcement learning; Dialogue management

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Chandramohan, S. (2012). Revisiting user simulation in dialogue systems : do we still need them ? : will imitation play the role of simulation ? : Revisiter la simulation d'utilisateurs dans les systèmes de dialogue parlé : est-elle encore nécessaire ? : est-ce que l'imitation peut jouer le rôle de la simulation ?. (Doctoral Dissertation). Avignon. Retrieved from http://www.theses.fr/2012AVIG0185

Chicago Manual of Style (16^th Edition):

Chandramohan, Senthilkumar. “Revisiting user simulation in dialogue systems : do we still need them ? : will imitation play the role of simulation ? : Revisiter la simulation d'utilisateurs dans les systèmes de dialogue parlé : est-elle encore nécessaire ? : est-ce que l'imitation peut jouer le rôle de la simulation ?.” 2012. Doctoral Dissertation, Avignon. Accessed December 15, 2019. http://www.theses.fr/2012AVIG0185.

MLA Handbook (7^th Edition):

Chandramohan, Senthilkumar. “Revisiting user simulation in dialogue systems : do we still need them ? : will imitation play the role of simulation ? : Revisiter la simulation d'utilisateurs dans les systèmes de dialogue parlé : est-elle encore nécessaire ? : est-ce que l'imitation peut jouer le rôle de la simulation ?.” 2012. Web. 15 Dec 2019.

Vancouver:

Chandramohan S. Revisiting user simulation in dialogue systems : do we still need them ? : will imitation play the role of simulation ? : Revisiter la simulation d'utilisateurs dans les systèmes de dialogue parlé : est-elle encore nécessaire ? : est-ce que l'imitation peut jouer le rôle de la simulation ?. [Internet] [Doctoral dissertation]. Avignon; 2012. [cited 2019 Dec 15]. Available from: http://www.theses.fr/2012AVIG0185.

Council of Science Editors:

Chandramohan S. Revisiting user simulation in dialogue systems : do we still need them ? : will imitation play the role of simulation ? : Revisiter la simulation d'utilisateurs dans les systèmes de dialogue parlé : est-elle encore nécessaire ? : est-ce que l'imitation peut jouer le rôle de la simulation ?. [Doctoral Dissertation]. Avignon; 2012. Available from: http://www.theses.fr/2012AVIG0185

University of Georgia

17. Bhat, Sanath Govinda. Learning driver preferences for freeway merging using multitask irl.

Degree: MS, Computer Science, 2017, University of Georgia

URL: http://hdl.handle.net/10724/37273

► Most automobile manufacturers today have invested heavily in the research and design of implementing autonomy in their cars. One important and challenging problem faced by… (more)

Subjects/Keywords: Inverse Reinforcement Learning; Hierarchical Bayesian Model; Multitask; Highway Merging; NGSIM; Likelihood Weighting

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Bhat, S. G. (2017). Learning driver preferences for freeway merging using multitask irl. (Masters Thesis). University of Georgia. Retrieved from http://hdl.handle.net/10724/37273

Chicago Manual of Style (16^th Edition):

Bhat, Sanath Govinda. “Learning driver preferences for freeway merging using multitask irl.” 2017. Masters Thesis, University of Georgia. Accessed December 15, 2019. http://hdl.handle.net/10724/37273.

MLA Handbook (7^th Edition):

Bhat, Sanath Govinda. “Learning driver preferences for freeway merging using multitask irl.” 2017. Web. 15 Dec 2019.

Vancouver:

Bhat SG. Learning driver preferences for freeway merging using multitask irl. [Internet] [Masters thesis]. University of Georgia; 2017. [cited 2019 Dec 15]. Available from: http://hdl.handle.net/10724/37273.

Council of Science Editors:

Bhat SG. Learning driver preferences for freeway merging using multitask irl. [Masters Thesis]. University of Georgia; 2017. Available from: http://hdl.handle.net/10724/37273

University of Georgia

18. Bhat, Sanath Govinda. Learning driver preferences for freeway merging using multitask irl.

Degree: MS, Computer Science, 2017, University of Georgia

URL: http://hdl.handle.net/10724/37116

► Most automobile manufacturers today have invested heavily in the research and design of implementing autonomy in their cars. One important and challenging problem faced by… (more)

Subjects/Keywords: Inverse Reinforcement Learning; Hierarchical Bayesian Model; Multitask; Highway Merging; NGSIM; Likelihood Weighting

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Bhat, S. G. (2017). Learning driver preferences for freeway merging using multitask irl. (Masters Thesis). University of Georgia. Retrieved from http://hdl.handle.net/10724/37116

Chicago Manual of Style (16^th Edition):

Bhat, Sanath Govinda. “Learning driver preferences for freeway merging using multitask irl.” 2017. Masters Thesis, University of Georgia. Accessed December 15, 2019. http://hdl.handle.net/10724/37116.

MLA Handbook (7^th Edition):

Bhat, Sanath Govinda. “Learning driver preferences for freeway merging using multitask irl.” 2017. Web. 15 Dec 2019.

Vancouver:

Bhat SG. Learning driver preferences for freeway merging using multitask irl. [Internet] [Masters thesis]. University of Georgia; 2017. [cited 2019 Dec 15]. Available from: http://hdl.handle.net/10724/37116.

Council of Science Editors:

Bhat SG. Learning driver preferences for freeway merging using multitask irl. [Masters Thesis]. University of Georgia; 2017. Available from: http://hdl.handle.net/10724/37116

Virginia Tech

19. Shiraev, Dmitry Eric. Inverse Reinforcement Learning and Routing Metric Discovery.

Degree: MS, Computer Science, 2003, Virginia Tech

URL: http://hdl.handle.net/10919/34728

► Uncovering the metrics and procedures employed by an autonomous networking system is an important problem with applications in instrumentation, traffic engineering, and game-theoretic studies of… (more)

Subjects/Keywords: Inverse Reinforcement Learning; Routing; Network Metrics

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Shiraev, D. E. (2003). Inverse Reinforcement Learning and Routing Metric Discovery. (Masters Thesis). Virginia Tech. Retrieved from http://hdl.handle.net/10919/34728

Chicago Manual of Style (16^th Edition):

Shiraev, Dmitry Eric. “Inverse Reinforcement Learning and Routing Metric Discovery.” 2003. Masters Thesis, Virginia Tech. Accessed December 15, 2019. http://hdl.handle.net/10919/34728.

MLA Handbook (7^th Edition):

Shiraev, Dmitry Eric. “Inverse Reinforcement Learning and Routing Metric Discovery.” 2003. Web. 15 Dec 2019.

Vancouver:

Shiraev DE. Inverse Reinforcement Learning and Routing Metric Discovery. [Internet] [Masters thesis]. Virginia Tech; 2003. [cited 2019 Dec 15]. Available from: http://hdl.handle.net/10919/34728.

Council of Science Editors:

Shiraev DE. Inverse Reinforcement Learning and Routing Metric Discovery. [Masters Thesis]. Virginia Tech; 2003. Available from: http://hdl.handle.net/10919/34728

Wright State University

20. Nalamothu, Abhishek. Abusive and Hate Speech Tweets Detection with Text Generation.

Degree: MS, Computer Science, 2019, Wright State University

URL: http://rave.ohiolink.edu/etdc/view?acc_num=wright1567510940365305

► According to a Pew Research study, 41% of Americans have personally experienced online harassment and two-thirds of Americans have witnessed harassment in 2017. Hence, online… (more)

▼ According to a Pew Research study, 41% of Americans have personally experienced online harassment and two-thirds of Americans have witnessed harassment in 2017. Hence, online harassment detection is vital for securing and sustaining the popularity and viability of online social networks. Machine learning techniques play a crucial role in automatic harassment detection. One of the challenges of using supervised approaches is training data imbalance. Existing text generation techniques can help augment the training data, but they are still inadequate and ineffective. This research explores the role of domain-specific knowledge to complement the limited training data available for training a text generator.We conduct domain-specific text generation by combining inverse reinforcement learning (IRL) with domain-specific knowledge. Our approach includes two adversarial nets, a text generator and a Reward Approximator (RA). The objective of the text generator is to generate domain-specific text that is hard to discriminate from the real-world domain-specific text. The objective of the reward approximator is to discriminate the generated domain-specific text from the real-world text. During adversarial training, the generator and the RA play a mini-max game and try to arrive at a win-win state. Ultimately, augmenting diversified and semantically meaningful, generated domain-specific data to the existing dataset improves detection of domain-specific text. In addition to developing the Generative Adversarial Network-based framework, we also present a novel evaluation that uses variants of the BLEU metric to measure the diversity of generated text; uses perplexity and cosine similarity to measure the quality of the generated text. Experimental results show that the proposed framework outperforms a previous baseline (IRL without domain knowledge) on harassment (i.e., Abusive and Hate speech) tweet generation. Additionally, the generated tweets effectively augment the training data for online abusive and hate speech detection (tweet classification) resulting in a 9% accuracy improvement in classification using the augmented training set compared to the existing training set. Advisors/Committee Members: Sheth, Amit (Advisor).

Subjects/Keywords: Computer Science; Text generation; Generative adversarial network; Inverse Reinforcement Learning; Online Harassment detection

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Nalamothu, A. (2019). Abusive and Hate Speech Tweets Detection with Text Generation. (Masters Thesis). Wright State University. Retrieved from http://rave.ohiolink.edu/etdc/view?acc_num=wright1567510940365305

Chicago Manual of Style (16^th Edition):

Nalamothu, Abhishek. “Abusive and Hate Speech Tweets Detection with Text Generation.” 2019. Masters Thesis, Wright State University. Accessed December 15, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=wright1567510940365305.

MLA Handbook (7^th Edition):

Nalamothu, Abhishek. “Abusive and Hate Speech Tweets Detection with Text Generation.” 2019. Web. 15 Dec 2019.

Vancouver:

Nalamothu A. Abusive and Hate Speech Tweets Detection with Text Generation. [Internet] [Masters thesis]. Wright State University; 2019. [cited 2019 Dec 15]. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=wright1567510940365305.

Council of Science Editors:

Nalamothu A. Abusive and Hate Speech Tweets Detection with Text Generation. [Masters Thesis]. Wright State University; 2019. Available from: http://rave.ohiolink.edu/etdc/view?acc_num=wright1567510940365305

University of Pennsylvania

21. Wen, Min. Reinforcement Learning With High-Level Task Specifications.

Degree: 2019, University of Pennsylvania

URL: https://repository.upenn.edu/edissertations/3509

► Reinforcement learning (RL) has been widely used, for example, in robotics, recommendation systems, and financial services. Existing RL algorithms typically optimize reward-based surrogates rather than… (more)

Subjects/Keywords: Game theory; Inverse reinforcement learning; Learning-based control; Learning from demonstration; Reinforcement learning; Temporal logic specifications; Artificial Intelligence and Robotics; Computer Sciences

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Wen, M. (2019). Reinforcement Learning With High-Level Task Specifications. (Thesis). University of Pennsylvania. Retrieved from https://repository.upenn.edu/edissertations/3509

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):

Wen, Min. “Reinforcement Learning With High-Level Task Specifications.” 2019. Thesis, University of Pennsylvania. Accessed December 15, 2019. https://repository.upenn.edu/edissertations/3509.

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

MLA Handbook (7^th Edition):

Wen, Min. “Reinforcement Learning With High-Level Task Specifications.” 2019. Web. 15 Dec 2019.

Vancouver:

Wen M. Reinforcement Learning With High-Level Task Specifications. [Internet] [Thesis]. University of Pennsylvania; 2019. [cited 2019 Dec 15]. Available from: https://repository.upenn.edu/edissertations/3509.

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

Council of Science Editors:

Wen M. Reinforcement Learning With High-Level Task Specifications. [Thesis]. University of Pennsylvania; 2019. Available from: https://repository.upenn.edu/edissertations/3509

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

Oregon State University

22. 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 December 15, 2019. http://hdl.handle.net/1957/13662.

MLA Handbook (7^th Edition):

Proper, Scott. “Scaling multiagent reinforcement learning.” 2009. Web. 15 Dec 2019.

Vancouver:

Proper S. Scaling multiagent reinforcement learning. [Internet] [Doctoral dissertation]. Oregon State University; 2009. [cited 2019 Dec 15]. 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

Oregon State University

23. 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 December 15, 2019. http://hdl.handle.net/1957/25199.

MLA Handbook (7^th Edition):

Mehta, Neville. “Hierarchical structure discovery and transfer in sequential decision problems.” 2011. Web. 15 Dec 2019.

Vancouver:

Mehta N. Hierarchical structure discovery and transfer in sequential decision problems. [Internet] [Doctoral dissertation]. Oregon State University; 2011. [cited 2019 Dec 15]. 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

24. Zhang, Ruohan. Action selection in modular reinforcement learning.

Degree: MSin Computer Sciences, Computer Sciences, 2014, University of Texas – Austin

URL: http://hdl.handle.net/2152/25916

► Modular reinforcement learning is an approach to resolve the curse of dimensionality problem in traditional reinforcement learning. We design and implement a modular reinforcement learning… (more)

Subjects/Keywords: Modular reinforcement learning; Action selection; Module weight

…in a RL problem with large state space. We propose to take a modular reinforcement learning… …introduces a test domain, and demonstrates our modular reinforcement learning algorithm. In Chapter… …Modular reinforcement learning [7, 10, 12, 20] decomposes original RL problem into… …results suggest modular reinforcement learning might be a promising approach to curse of… …dimensionality problem. A close relative to modular reinforcement learning is hierarchical…

10 more images…

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Zhang, R. (2014). Action selection in modular reinforcement learning. (Masters Thesis). University of Texas – Austin. Retrieved from http://hdl.handle.net/2152/25916

Chicago Manual of Style (16^th Edition):

Zhang, Ruohan. “Action selection in modular reinforcement learning.” 2014. Masters Thesis, University of Texas – Austin. Accessed December 15, 2019. http://hdl.handle.net/2152/25916.

MLA Handbook (7^th Edition):

Zhang, Ruohan. “Action selection in modular reinforcement learning.” 2014. Web. 15 Dec 2019.

Vancouver:

Zhang R. Action selection in modular reinforcement learning. [Internet] [Masters thesis]. University of Texas – Austin; 2014. [cited 2019 Dec 15]. Available from: http://hdl.handle.net/2152/25916.

Council of Science Editors:

Zhang R. Action selection in modular reinforcement learning. [Masters Thesis]. University of Texas – Austin; 2014. Available from: http://hdl.handle.net/2152/25916

University of Illinois – Chicago

25. Monfort, Mathew. Methods in Large Scale Inverse Optimal Control.

Degree: 2016, University of Illinois – Chicago

URL: http://hdl.handle.net/10027/21540

► As our technology continues to evolve, so does the complexity of the problems that we expect our systems to solve. The challenge is that these… (more)

Subjects/Keywords: machine learning; artificial intelligence; inverse optimal control; graph search; autonomous agents; reinforcement learning; path distributions; robotic control; robotics; robots; activity recognition

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

Monfort, M. (2016). Methods in Large Scale Inverse Optimal Control. (Thesis). University of Illinois – Chicago. Retrieved from http://hdl.handle.net/10027/21540

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):

Monfort, Mathew. “Methods in Large Scale Inverse Optimal Control.” 2016. Thesis, University of Illinois – Chicago. Accessed December 15, 2019. http://hdl.handle.net/10027/21540.

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

MLA Handbook (7^th Edition):

Monfort, Mathew. “Methods in Large Scale Inverse Optimal Control.” 2016. Web. 15 Dec 2019.

Vancouver:

Monfort M. Methods in Large Scale Inverse Optimal Control. [Internet] [Thesis]. University of Illinois – Chicago; 2016. [cited 2019 Dec 15]. Available from: http://hdl.handle.net/10027/21540.

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

Council of Science Editors:

Monfort M. Methods in Large Scale Inverse Optimal Control. [Thesis]. University of Illinois – Chicago; 2016. Available from: http://hdl.handle.net/10027/21540

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

26. NGUYEN QUOC PHONG. AN ALTERNATIVE INFORMATION-THEORETIC CRITERION FOR ACTIVE LEARNING.

Degree: 2018, National University of Singapore

URL: http://scholarbank.nus.edu.sg/handle/10635/150065

Subjects/Keywords: active learning; mutual information; inverse reinforcement learning

Record Details Similar Records Cite « Share

❌

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

APA (6^th Edition):

PHONG, N. Q. (2018). AN ALTERNATIVE INFORMATION-THEORETIC CRITERION FOR ACTIVE LEARNING. (Thesis). National University of Singapore. Retrieved from http://scholarbank.nus.edu.sg/handle/10635/150065

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):

PHONG, NGUYEN QUOC. “AN ALTERNATIVE INFORMATION-THEORETIC CRITERION FOR ACTIVE LEARNING.” 2018. Thesis, National University of Singapore. Accessed December 15, 2019. http://scholarbank.nus.edu.sg/handle/10635/150065.

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

MLA Handbook (7^th Edition):

PHONG, NGUYEN QUOC. “AN ALTERNATIVE INFORMATION-THEORETIC CRITERION FOR ACTIVE LEARNING.” 2018. Web. 15 Dec 2019.

Vancouver:

PHONG NQ. AN ALTERNATIVE INFORMATION-THEORETIC CRITERION FOR ACTIVE LEARNING. [Internet] [Thesis]. National University of Singapore; 2018. [cited 2019 Dec 15]. Available from: http://scholarbank.nus.edu.sg/handle/10635/150065.

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

Council of Science Editors:

PHONG NQ. AN ALTERNATIVE INFORMATION-THEORETIC CRITERION FOR ACTIVE LEARNING. [Thesis]. National University of Singapore; 2018. Available from: http://scholarbank.nus.edu.sg/handle/10635/150065

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

Oregon State University

27. 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 December 15, 2019. 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. 15 Dec 2019.

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 2019 Dec 15]. 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

University of Illinois – Urbana-Champaign

28. 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 December 15, 2019. 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. 15 Dec 2019.

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 2019 Dec 15]. 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

Delft University of Technology

29. 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 December 15, 2019. 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. 15 Dec 2019.

Vancouver:

Van Diepen MDM. Avoiding failure states during reinforcement learning:. [Internet] [Masters thesis]. Delft University of Technology; 2011. [cited 2019 Dec 15]. 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

30. 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 December 15, 2019. 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. 15 Dec 2019.

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 2019 Dec 15]. 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

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

Open Access Theses and Dissertations