A Strongly Typed GP-Based Video Game Player

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

  author =       "Baozhu Jia and Marc Ebner",
  title =        "A Strongly Typed GP-Based Video Game Player",
  booktitle =    "Proceedings of the IEEE Conference on Computational
                 Intelligence and Games (CIG-2015)",
  year =         "2015",
  editor =       "Shi-Jim Yen and Tristan Cazenave and Philip Hingston",
  pages =        "299--305",
  address =      "Tainan, Taiwan",
  month =        aug # " 31-" # sep # " 2",
  publisher =    "IEEE",
  keywords =     "genetic algorithms, genetic programming, STGP,
                 Py-vgdl, AI, MCTS, Atari 2600 Space Invaders, Frogger,
                 Missile Command.",
  DOI =          "doi:10.1109/CIG.2015.7317920",
  size =         "7 pages",
  abstract =     "This paper attempts to evolve a general video game
                 player, i.e. an agent which is able to learn to play
                 many different video games with little domain
                 knowledge. Our project uses strongly typed genetic
                 programming as a learning algorithm. Three simple
                 hand-crafted features are chosen to represent the game
                 state. Each feature is a vector which consists of the
                 position and orientation of each game object that is
                 visible on the screen. These feature vectors are handed
                 to the learning algorithm which will output the action
                 the game player will take next. Game knowledge and
                 feature vectors are acquired by processing screen grabs
                 from the game. Three different video games are used to
                 test the algorithm. Experiments show that our algorithm
                 is able to find solutions to play all these three games
  notes =        "ECJ. RGB to grey scale and downscaled screen grab, 3
                 sets of high level terminals: no difference between
                 them found. Importance of STGP unclear: types seem to
                 be void, boolean and float.

                 15:30 http://cig2015.nctu.edu.tw/program",

Genetic Programming entries for Baozhu Jia Marc Ebner