In this work was offered an adjustments of techniques and methods of artificial intelligence for computer player, in two-players combat games. There was tried to adapt the artificial intelligence to the computer player, with those proposed techniques and methods in this type of games. Also was investigated whether those proposed techniques and methods suits for this class of computer games. In this work also was analyzed agent learning speed, on what depends it and explored the factors that determines the rapid learning speed and efficient use of agent knowledge. Discovered and investigated factors were fitted to the rapid learning speed and efficient use of agent knowledge.


    Access

    Download


    Export, share and cite



    Title :

    Mokymo pastiprinimu metodų pritaikymas kompiuterinio žaidimo personažui interaktyvioje 2D/3D grafikos sistemoje ; An adaptation of reinforcement learning methods to the computer game character in interactive 2D/3D graphic system



    Publication date :

    2011-05-30


    Type of media :

    Theses


    Type of material :

    Electronic Resource


    Language :

    Lithuanian , English



    Classification :

    DDC:    629