Abstract for HONS 02/20 - Computer Science and Software Engineering - University of Canterbury - New Zealand

Abstract for HONS 02/20

Transfer Learning in Discrete Zero-Sum Games

Nathan Cleaver
Department of Computer Science and Software Engineering
University of Canterbury

Abstract

The construction of a general artificial intelligence is a long-standing goal of computer science. Transfer learning, the ability to transfer knowledge from one context to another, is an essential component of a general intelligence. This work investigates the effects of transfer learning in discrete, zero-sum games. We use distributed parallel Monte Carlo Tree Search to construct game-playing models for chess and a chess variant, Chessplus. Transfer learning is used to allow the chess model to play Chessplus, and results measured. To this end, we also introduce a novel pruning algorithm for Monte Carlo Tree Search. We demonstrate that positive transfer learning in Monte Carlo Tree Search is possible, and in our work, highly successful. The model with transfer outperforms the model without, winning 47.4% of games and drawing 16.9%. Statistical analysis supports the validity of our results. Further analyses offer valuable insights into the specific benefits of transfer between these two domains.
  • Phone: +64 3 369 2777
    Fax: +64 3 364 2569
    CSSEadministration@canterbury.ac.nz
  • Computer Science and Software Engineering
    University of Canterbury
    Private Bag 4800, Christchurch
    New Zealand
  • Follow us
    FacebookYoutubetwitterLinked In