Multi-task Learning in Atari Video Games with Emergent Tangled Program Graphs

Created by W.Langdon from gp-bibliography.bib Revision:1.4549

  author =       "Stephen Kelly and Malcolm I. Heywood",
  title =        "Multi-task Learning in {Atari} Video Games with
                 Emergent Tangled Program Graphs",
  booktitle =    "Proceedings of the Genetic and Evolutionary
                 Computation Conference",
  series =       "GECCO '17",
  year =         "2017",
  isbn13 =       "978-1-4503-4920-8",
  address =      "Berlin, Germany",
  pages =        "195--202",
  size =         "8 pages",
  URL =          "",
  DOI =          "doi:10.1145/3071178.3071303",
  acmid =        "3071303",
  publisher =    "ACM",
  publisher_address = "New York, NY, USA",
  keywords =     "genetic algorithms, genetic programming, emergent
                 modularity, multi-task learning",
  month =        "15-19 " # jul,
  abstract =     "The Atari 2600 video game console provides an
                 environment for investigating the ability to build
                 artificial agent behaviours for a variety of games
                 using a common interface. Such a task has received
                 attention for addressing issues such as: 1) operation
                 directly from a high-dimensional game screen; and 2)
                 partial observability of state. However, a general
                 theme has been to assume a common machine learning
                 algorithm, but completely retrain the model for each
                 game title. Success in this respect implies that agent
                 behaviours can be identified without hand crafting game
                 specific attributes/actions. This work advances current
                 state-of-the-art by evolving solutions to play multiple
                 titles from the same run. We demonstrate that in
                 evolving solutions to multiple game titles, agent
                 behaviours for an individual game as well as single
                 agents capable of playing all games emerge from the
                 same evolutionary run. Moreover, the computational cost
                 is no more than that used for building solutions for a
                 single title. Finally, while generally matching the
                 skill level of controllers from neuro-evolution/deep
                 learning, the genetic programming solutions evolved
                 here are several orders of magnitude simpler, resulting
                 in real-time operation at a fraction of the cost.",
  notes =        "Also known as \cite{Kelly:2017:MLA:3071178.3071303}
                 GECCO-2017 A Recombination of the 26th International
                 Conference on Genetic Algorithms (ICGA-2017) and the
                 22nd Annual Genetic Programming Conference (GP-2017)",

Genetic Programming entries for Stephen Kelly Malcolm Heywood