Douzero: Mastering Doudizhu With Self-play Deep Reinforcement Learning

Abstract

Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents. While significant achievements have been made in various perfect- and imperfect-information games, DouDizhu (a.k.a. Fighting the Landlord), a three-player card game, is still unsolved. DouDizhu is a very challenging domain with competition, collaboration, imperfect information, large state space, and particularly a massive set of possible actions where the legal actions vary significantly from turn to turn. Unfortunately, modern reinforcement learning algorithms mainly focus on simple and small action spaces, and not surprisingly, are shown not to make satisfactory progress in DouDizhu. In this work, we propose a conceptually simple yet effective DouDizhu AI system, namely DouZero, which enhances traditional Monte-Carlo methods with deep neural networks, action encoding, and parallel actors. Starting from scratch in a single server with four GPUs, DouZero outperformed all

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzha2021douzero

Related papers

• Danzero: Mastering Guandan Game With Reinforcement Learning (2022)6.77
• Perfectdou: Dominating Doudizhu With Perfect Information Distillation (2022)0.00
• Danzero+: Dominating The Guandan Game Through Reinforcement Learning (2023)0.00
• Simplified Action Decoder For Deep Multi-agent Reinforcement Learning (2019)4.03
• Mastering Complex Control In MOBA Games With Deep Reinforcement Learning (2019)0.00
• Reinforcement Learning In Two Player Zero Sum Simultaneous Action Games (2021)0.00
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• Tizero: Mastering Multi-agent Football With Curriculum Learning And Self-play (2023)2.26