Mastering the Game of Guandan with Deep Reinforcement Learning and Behavior Regulating
This work addresses the problem of decision-making in a challenging game for AI research, but it appears incremental as it builds on existing methods like Monte-Carlo and deep neural networks.
The paper tackles the challenge of mastering the complex game of Guandan by proposing the GuanZero framework, which uses deep reinforcement learning and behavior regulation, and demonstrates its effectiveness by comparing it with state-of-the-art approaches.
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 methods and deep neural networks. The main contribution of this paper is about regulating agents' behavior through a carefully designed neural network encoding scheme. We then demonstrate the effectiveness of the proposed framework by comparing it with state-of-the-art approaches.