• Login
    View Item 
    •   Home
    • Massey Documents by Type
    • Theses and Dissertations
    • View Item
    •   Home
    • Massey Documents by Type
    • Theses and Dissertations
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Genetic network programming with reinforcement learning and optimal search component : a thesis presented in partial fulfilment of the requirements for the degree of Master of Science in Computer Sciences at Massey University, Auckland, New Zealand

    Icon
    View/Open Full Text
    AlshehriMScThesis.pdf (3.620Mb)
    Export to EndNote
    Abstract
    This thesis presents ways of improving the genetic composition, structure and learning strategies for a graph-based evolutionary algorithm, called Genetic Networking Programming with Reinforcement Learning (GNP-RL), particularly when working with multi-agent and dynamic environments. GNP-RL is an improvement over Genetic Programming, allowing for the concise representation of solutions in terms of a networked graph structure and uses RL to further refine the graph solutions. This work has improved GNP-RL by combining three new techniques: Firstly, it has added a reward and punishment scheme as part of its learning strategy that supports constraint conformance, allowing for a more adaptive training of the agent, so that it can learn how to avoid unwanted situations more effectively. Secondly, an optimal search algorithm has been combined in the GNP-RL core to get an accurate analysis of the exploratory environment. Thirdly, a task prioritization technique has been added to the agent’s learning by giving promotional rewards, so they are trained on how to take priority into account when performing tasks. In this thesis, we applied the improved algorithm to the Tile World benchmarking testbed, which is considered as one of the standard complex problems in this domain, having only a sparse training set. Our experiment results show that the proposed algorithm is superior than the best existing variant of the GNP-RL algorithm [1]. We have achieved 86.66% test accuracy on the standard benchmarking dataset [2]. In addition, we have created another benchmarking dataset, similar in complexity to the one proposed in [1], to test the proposed algorithms further, where it achieved a test accuracy of 96.66%; that is 33.66% more accurate.
    Date
    2019
    Author
    Alshehri, Mona Abdulrahman M
    Publisher
    Massey University
    URI
    http://hdl.handle.net/10179/15591
    Collections
    • Theses and Dissertations
    Metadata
    Show full item record

    Copyright © Massey University
    Contact Us | Send Feedback | Copyright Take Down Request | Massey University Privacy Statement
    DSpace software copyright © Duraspace
    v5.7-2020.1
     

     

    Tweets by @Massey_Research
    Information PagesContent PolicyDepositing content to MROCopyright and Access InformationDeposit LicenseDeposit License SummaryTheses FAQFile FormatsDoctoral Thesis Deposit

    Browse

    All of MROCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Statistics

    View Usage Statistics

    Copyright © Massey University
    Contact Us | Send Feedback | Copyright Take Down Request | Massey University Privacy Statement
    DSpace software copyright © Duraspace
    v5.7-2020.1