EvoMCTS: A Scalable Approach for General Game Learning

Created by W.Langdon from gp-bibliography.bib Revision:1.4524

  author =       "Amit Benbassat and Moshe Sipper",
  journal =      "IEEE Transactions on Computational Intelligence and AI
                 in Games",
  title =        "{EvoMCTS:} A Scalable Approach for General Game
  year =         "2014",
  volume =       "6",
  number =       "4",
  pages =        "382--394",
  month =        dec,
  keywords =     "genetic algorithms, genetic programming, STGP, MCTS,
                 Board Games, Monte Carlo Methods, Search",
  DOI =          "doi:10.1109/TCIAIG.2014.2306914",
  ISSN =         "1943-068X",
  size =         "29 pages",
  abstract =     "We present the application of genetic programming as a
                 generic game learning approach to zero-sum,
                 deterministic, full knowledge board games by evolving
                 board-state evaluation functions to be used in
                 conjunction with Monte Carlo Tree Search (MCTS). Our
                 method involves evolving board-evaluation functions
                 that are then used to guide the MCTS play out strategy.
                 We examine several variants of Reversi, Dodgem, and Hex
                 using strongly typed genetic programming, explicitly
                 defined introns, and a selective directional crossover
                 method. Our results show a proficiency that surpasses
                 that of baseline handcrafted players using equal and in
                 some cases a greater amount of search, with little
                 domain knowledge and no expert domain knowledge.
                 Moreover, our results exhibit scalability.",
  notes =        "Also known as \cite{6744581}",

Genetic Programming entries for Amit Benbassat Moshe Sipper