Evolving simple programs for playing atari games - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Evolving simple programs for playing atari games

Abstract

Cartesian Genetic Programming (CGP) has previously shown capabilities in image processing tasks by evolving programs with a function set specialized for computer vision. A similar approach can be applied to Atari playing. Programs are evolved using mixed type CGP with a function set suited for matrix operations, including image processing, but allowing for controller behavior to emerge. While the programs are relatively small, many controllers are competitive with state of the art methods for the Atari benchmark set and require less training time. By evaluating the programs of the best evolved individuals, simple but effective strategies can be found.
Fichier principal
Vignette du fichier
wilson_22615.pdf (339.31 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03622977 , version 1 (29-03-2022)

Identifiers

  • HAL Id : hal-03622977 , version 1
  • OATAO : 22615

Cite

Dennis Wilson, Sylvain Cussat-Blanc, Hervé Luga, Julian Miller. Evolving simple programs for playing atari games. Genetic and Evolutionary Computation COnference (GECCO 2018), Jul 2018, Kyoto, Japan. pp.229-236. ⟨hal-03622977⟩
12 View
11 Download

Share

Gmail Mastodon Facebook X LinkedIn More