• Login
    View Item 
    •   MINDS@UW Home
    • MINDS@UW Whitewater
    • Master's Theses--UW-Whitewater
    • View Item
    •   MINDS@UW Home
    • MINDS@UW Whitewater
    • Master's Theses--UW-Whitewater
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Emergent behavior in neuroevolved agents

    Thumbnail
    File(s)
    CS_master_thesis_Brian_Maresso.pdf (327.7Kb)
    Date
    2018-11
    Author
    Maresso, Brian
    Publisher
    University of Wisconsin--Whitewater
    Advisor(s)
    Nguyen, Hien
    Mukherjee, Lopamudra
    Zhou, Jiazhen
    Metadata
    Show full item record
    Abstract
    Neural networks have been widely used for their ability to create generalized rulesets for a given set of training data. In applications where no such training data exists such as new video games, they are often overlooked in favor of hard-coded artificial intelligence behaviors. By applying a genetic algorithm instead of the traditional back-propagation technique, neural networks can develop video game AI while not requiring training data or preexisting knowledge of their environment. This natural approach leads to more natural ‘human-like’ behavior both in terms of the learning process and in qualitative analysis. In this thesis, we evaluate the ability of neuroevolved videogame AI to show human-like learning patterns and adaptability to new environments. For applications in videogames or computer simulations, we explore how a set of hyperparameters can be modified to achieve the desired level of intelligence or difficulty- a key factor for videogame AI. The prospect of changing hyperparameters then passively waiting for training to complete offers an attractive alternative to hard-coded AI where new behaviors would have to be actively written and tested. Our evaluations focus on evolving AI for a simple car racing videogame. We found that our approach was indeed capable of creating a suitable AI for our test environments, and we were able to evolve new behaviors using both old ones (adaptation) and new ones (learning from scratch). Our process could be repeated for other game genres or applications, presumably with similar success.
    Subject
    Neural networks (Computer science)
    Genetic algorithms
    Artificial intelligence
    Machine learning
    Video games
    Reinforcement learning
    Permanent Link
    http://digital.library.wisc.edu/1793/78967
    Description
    This file was last viewed in Microsoft Edge.
    Part of
    • Master's Theses--UW-Whitewater

    Contact Us | Send Feedback
     

     

    Browse

    All of MINDS@UWCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

    My Account

    LoginRegister

    Contact Us | Send Feedback