English

CogniPlay: a work-in-progress Human-like model for General Game Playing

Artificial Intelligence 2025-07-09 v1

Abstract

While AI systems have equaled or surpassed human performance in a wide variety of games such as Chess, Go, or Dota 2, describing these systems as truly "human-like" remains far-fetched. Despite their success, they fail to replicate the pattern-based, intuitive decision-making processes observed in human cognition. This paper presents an overview of findings from cognitive psychology and previous efforts to model human-like behavior in artificial agents, discusses their applicability to General Game Playing (GGP) and introduces our work-in-progress model based on these observations: CogniPlay.

Keywords

Cite

@article{arxiv.2507.05868,
  title  = {CogniPlay: a work-in-progress Human-like model for General Game Playing},
  author = {Aloïs Rautureau and Éric Piette},
  journal= {arXiv preprint arXiv:2507.05868},
  year   = {2025}
}

Comments

5 pages, 1 figure

R2 v1 2026-07-01T03:51:10.883Z