Mastering the Game of Guandan with Deep Reinforcement Learning and Behavior Regulating

arXiv:2402.13582v1 Announce Type: cross
Abstract: Games are a simplified model of reality and often serve as a favored platform for Artificial Intelligence (AI) research. Much of the research is concerned with game-playing agents and their decision making processes. The game of Guandan (literally, "throwing eggs") is a challenging game where even professional human players struggle to make the right decision at times. In this paper we propose a framework named GuanZero for AI agents to master this game using Monte-Carlo …

abstract agents artificial artificial intelligence arxiv behavior cs.ai cs.lg decision decision making eggs game games intelligence making platform playing processes reality reinforcement reinforcement learning research serve simplified type