• DocumentCode
    3683560
  • Title

    The geometry friends game AI competition

  • Author

    Rui Prada;Phil Lopes;João Catarino;Joao Quitério;Francisco S. Melo

  • Author_Institution
    INESC-ID and Institute Superior Té
  • fYear
    2015
  • Firstpage
    431
  • Lastpage
    438
  • Abstract
    This paper describes a new game AI competition that engages participants in the creation of agents for a cooperative platform puzzle game. The agents face the challenge of acting in a dynamic environment, with friction and gravity, as they coordinate actions to solve cooperative puzzles. Hence, agents need to devise cooperative plans to solve the puzzles in the most efficient way and to coordinate their actions to perform joint actions in real-time. The core of the competition is the cooperative track that requires the development of two distinct agents, but we also include a single player track for participants that want to craft the basic skills of the agent without the complexity of cooperation. In particular, to cope with understanding the topology of a level in order to define a plan for solving the puzzle or to define mechanisms to act well in the physics-based game environment. We present the results of the 2014 competition held at IEEE Conference on Computational Intelligence in Games, in Dortmund, and discuss some future directions of research.
  • Keywords
    "Games","Artificial intelligence","Diamonds","Geometry","Tracking","Friction","Gravity"
  • Publisher
    ieee
  • Conference_Titel
    Computational Intelligence and Games (CIG), 2015 IEEE Conference on
  • ISSN
    2325-4270
  • Electronic_ISBN
    2325-4289
  • Type

    conf

  • DOI
    10.1109/CIG.2015.7317949
  • Filename
    7317949