Exploiting Reward Machines with Deep Reinforcement Learning in Continuous Action Domains

Simple item page
dc.contributor.advisorLesperance, Yves
dc.contributor.authorSun, Haolin
dc.date.accessioned2023-03-28T21:23:20Z
dc.date.available2023-03-28T21:23:20Z
dc.date.copyright2022-12-07
dc.date.issued2023-03-28
dc.date.updated2023-03-28T21:23:19Z
dc.degree.disciplineComputer Science
dc.degree.levelMaster's
dc.degree.nameMSc - Master of Science
dc.description.abstractDeep reinforcement learning can solve real-world robot control problems, such as autonomous driving and robotic arm manipulation. In deep reinforcement learning, an agent does not know the problem description and learns the optimal solution through trial-and-error. This method brings two major challenges when solving real-world problems: partial observability and learning efficiency. In this thesis, we address these two challenges and extend previous work. First, we use reward machines to address the problem of partial observability. Then, we focus on finding the existing cutting-edge deep reinforcement learning algorithms and integrating them with reward machines to enhance the learning efficiency. To test the performance of all the algorithms, we proposed a series of different tasks that can be used to mimic real-world robot control problems. Finally, based on the test results, we compare the performance of all the algorithms and analyze their advantages and disadvantages.
dc.identifier.urihttp://hdl.handle.net/10315/41039
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subject.keywordsMachine learning
dc.subject.keywordsReinforcement learning
dc.subject.keywordsReward machine
dc.subject.keywordsDeep reinforcement learning
dc.subject.keywordsQ-learning
dc.subject.keywordsDDPG
dc.subject.keywordsSAC
dc.subject.keywordsTD3
dc.subject.keywordsPPO
dc.subject.keywordsPartial observability
dc.subject.keywordsRobotic control
dc.titleExploiting Reward Machines with Deep Reinforcement Learning in Continuous Action Domains
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Sun_Haolin_HS_2023_Masters.pdf
Size:
2.9 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Computer Science

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.