ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Implementation of Backgammon player with neural network

Primož Gajski (2010) Implementation of Backgammon player with neural network. EngD thesis.

[img] PDF
Download (2465Kb)


    Diploma thesis Implementation of Backgammon player with neural network describes implementation of how is a computer capable to learn the game of backgammon. It is achieved with computer playing against itself, without any human help and without any prior knowledge about the game. Evaluation function of game positions, according to the thrown dice and checker positions, was implemented with neural network. Neural network is presented as a 2-layer perceptron. The learning of neural network was achieved with reinforcement learning and backpropagation algorithm. Within backpropagation algorithm neural network plays several milions of backgammon games to achieve the advanced level of the game. Testing was also performed without any human interaction. Neural network played backgammon game against so called pubeval player, who also uses for its logic evaluation function to play on strong intermediate level. The testing showed that the neural network successfully accomplished all basic and also many of advanced features of game playing elements. Diploma work also involves realization of graphical user interface, which allows user to play backgammon against neural network.

    Item Type: Thesis (EngD thesis)
    Keywords: backgammon, neural network, perceptron, reinforcement learning, backpropagation algorithm
    Number of Pages: 45
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    izr. prof. dr. Branko Šter283Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(ID=7671124)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 1060
    Date Deposited: 15 Apr 2010 11:13
    Last Modified: 13 Aug 2011 00:37
    URI: http://eprints.fri.uni-lj.si/id/eprint/1060

    Actions (login required)

    View Item