The Application of Co-evolutionary Genetic Programming and TD(1) Reinforcement Learning in Large-Scale Strategy Game VCMI

Created by W.Langdon from gp-bibliography.bib Revision:1.4496

  title =        "The Application of Co-evolutionary Genetic Programming
                 and {TD}(1) Reinforcement Learning in Large-Scale
                 Strategy Game {VCMI}",
  author =       "Lukasz Wilisowski and Rafal Drezewski",
  booktitle =    "9th KES International Conference on Agent and
                 Multi-Agent Systems: Technologies and Applications,
                 KES-AMSTA 2015",
  year =         "2015",
  editor =       "Gordan Jezic and Robert J. Howlett and 
                 Lakhmi C. Jain",
  volume =       "38",
  series =       "Smart Innovation, Systems and Technologies",
  pages =        "81--93",
  address =      "Sorrento, Italy",
  month =        jun # " 17-19",
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming, neural
                 networks, strategy games",
  isbn13 =       "978-3-319-19728-9",
  bibdate =      "2017-05-21",
  bibsource =    "DBLP,
  DOI =          "doi:10.1007/978-3-319-19728-9_7",
  abstract =     "VCMI is a new, open-source project that could become
                 one of the biggest testing platform for modern AI
                 algorithms in the future. Its complex environment and
                 turn-based game play make it a perfect system for any
                 AI driven solution. It also has a large community of
                 active players which improves the testability of target
                 algorithms. This paper explores VCMI's environment and
                 tries to assess its complexity by providing a base
                 solution for battle handling problem using two global
                 optimisation algorithms: Co-Evolution of Genetic
                 Programming Trees and TD(1) algorithm with Back
                 Propagation neural network. Both algorithms have been
                 used in VCMI to evolve battle strategies through a
                 fully autonomous learning process. Finally, the
                 obtained strategies have been tested against existing
                 solutions and compared with players' best tactics.",

Genetic Programming entries for Lukasz Wilisowski Rafal Drezewski