Design and evaluation of a hybrid multi-task learning model for optimizing deep reinforcement learning agents

dc.contributor.advisorMahmoud, Qusay H.
dc.contributor.authorVithayathil Varghese, Nelson
dc.date.accessioned2021-05-28T19:28:20Z
dc.date.accessioned2022-03-29T16:46:09Z
dc.date.available2021-05-28T19:28:20Z
dc.date.available2022-03-29T16:46:09Z
dc.date.issued2021-04-01
dc.degree.disciplineElectrical and Computer Engineering
dc.degree.levelMaster of Applied Science (MASc)
dc.description.abstractDriven by recent technological advancements within the artificial intelligence domain, deep learning has emerged as a promising representation learning technique. This in turn has given rise to the evolution of deep reinforcement learning that combines deep learning with reinforcement learning methods. Subsequently, performance optimization achieved by reinforcement learning intelligent agents designed with model-free based approaches were predominantly limited to systems with reinforcement learning algorithms learning single task. Such a model was found to be quite data inefficient, whenever agents needed to interact with more complex, rich data environments. This thesis introduces a hybrid multi-task learning-oriented approach for optimization of deep reinforcement learning agents operating within different but semantically similar environments with related tasks. Empirical results obtained with OpenAI Gym library-based Atari 2600 video gaming environment demonstrate that the proposed hybrid multi-task learning model is successful in addressing key challenges associated with the performance optimization of deep reinforcement learning agents.en
dc.description.sponsorshipUniversity of Ontario Institute of Technologyen
dc.identifier.urihttps://hdl.handle.net/10155/1303
dc.language.isoenen
dc.subjectDeep reinforcement learningen
dc.subjectNeural networksen
dc.subjectDeep learningen
dc.subjectMulti-task learningen
dc.subjectActor-criticen
dc.titleDesign and evaluation of a hybrid multi-task learning model for optimizing deep reinforcement learning agentsen
dc.typeThesisen
thesis.degree.disciplineElectrical and Computer Engineering
thesis.degree.grantorUniversity of Ontario Institute of Technology
thesis.degree.nameMaster of Applied Science (MASc)

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Vithayathil_Varghese_Nelson.pdf
Size:
3.35 MB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.61 KB
Format:
Plain Text
Description: