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

TL;DR

CogniPlay is an ongoing project aiming to develop a human-like AI model for General Game Playing by integrating insights from cognitive psychology to emulate human decision-making patterns.

Contribution

The paper introduces CogniPlay, a novel work-in-progress model that incorporates cognitive psychology principles to enhance human-like behavior in GGP agents.

Findings

Reviewed cognitive psychology insights relevant to GGP

Identified gaps in current AI models' human-like decision-making

Proposed initial framework for CogniPlay

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.