Discovering Agent Behaviours through Code Reuse: Examples from Half-Field Offense and Ms. Pac-Man

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

@Article{Kelly:2017:ieeeTCIAIgames,
  author =       "Stephen Kelly and Malcolm I. Heywood",
  title =        "Discovering Agent Behaviours through Code Reuse:
                 Examples from Half-Field Offense and {Ms. Pac-Man}",
  journal =      "IEEE Transactions on Games",
  year =         "2018",
  volume =       "10",
  number =       "2",
  pages =        "195--208",
  month =        jun,
  keywords =     "genetic algorithms, genetic programming, code reuse,
                 coevolution, half-field offense (HFO), Ms Pac-Man, task
                 transfer",
  DOI =          "doi:10.1109/TCIAIG.2017.2766980",
  ISSN =         "1943-068X",
  size =         "14 pages",
  abstract =     "This work demonstrates how code reuse allows genetic
                 programming (GP) to discover strategies for difficult
                 gaming scenarios while maintaining relatively low model
                 complexity. Critical factors in the proposed approach
                 are illustrated through an in-depth study in two
                 challenging task domains: RoboCup Soccer and Ms.
                 Pac-Man. In RoboCup, we demonstrate how policies
                 initially evolved for simple subtasks can be reused,
                 with no additional training or transfer function, in
                 order to improve learning in the complex Half Field
                 Offense (HFO) task. We then show how the same approach
                 to code reuse can be applied directly in Ms. Pac-Man.
                 In the later case, the use of task-agnostic diversity
                 maintenance removes the need to explicitly identify
                 suitable subtasks a priori. The resulting GP policies
                 achieve state-of-the-art levels of play in HFO and
                 surpass scores previously reported in the Ms. Pac-Man
                 literature, while employing less domain knowledge
                 during training. Moreover, the highly modular policies
                 discovered by GP are shown to be significantly less
                 complex than state-of-the-art solutions in both
                 domains. Throughout this work we pay special attention
                 to a pair of task-agnostic diversity maintenance
                 techniques, and empirically demonstrate their
                 importance to the development of strong policies.",
  notes =        "Also known as \cite{8085186}",
}

Genetic Programming entries for Stephen Kelly Malcolm Heywood

Citations