CogniPlay: a work-in-progress Human-like model for General Game Playing
This work addresses the gap in developing truly human-like AI for games, which could enhance AI adaptability and cognitive modeling, but it is incremental as it builds on existing research and is still in progress.
The paper tackles the problem of creating human-like AI for General Game Playing by reviewing cognitive psychology and prior models, and introduces a work-in-progress model called CogniPlay to replicate intuitive human decision-making.
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.