• Login
    View Item 
    •   eScholar Home
    • Faculty of Engineering & Applied Science
    • Master Theses & Projects
    • View Item
    •   eScholar Home
    • Faculty of Engineering & Applied Science
    • Master Theses & Projects
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

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

    Thumbnail
    View/Open
    Vithayathil_Varghese_Nelson.pdf (3.346Mb)
    Date
    2021-04-01
    Author
    Vithayathil Varghese, Nelson
    Metadata
    Show full item record
    Abstract
    Driven 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.
    URI
    https://hdl.handle.net/10155/1303
    Collections
    • Electronic Theses and Dissertations [1323]
    • Master Theses & Projects [418]

    Related items

    Showing items related by title, author, creator and subject.

    • Professors and instructors' experiences with transitions and policies for the online environment 

      Francis, Roger (2012-08-01)
      Professors develop policies and procedures for their courses that are relevant and applicable for their classroom or learning platform. In particular, professors transitioning from a traditional to an online (synchronous ...
    • Using machine learning methods to aid scientists in laboratory environments 

      Coles, Rory (2019-12-01)
      As machine learning gains popularity as a scientific instrument, we look to create methods to implement it as a laboratory tool for researchers. In the first of two projects, we discuss creating a real-time interference ...
    • On deep learning in physics 

      Mills, Kyle (2021-04-01)
      Machine learning, and most notably deep neural networks, have seen unprecedented success in recent years due to their ability to learn complex nonlinear mappings by ingesting large amounts of data through the process of ...

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of eScholarCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV