mlsanityData to 7 Oct 2026

DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning

arXiv 2204.02558 ↗First posted 6 Apr 2022cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Recent years have witnessed the great breakthrough of deep reinforcement learning (DRL) in various perfect and imperfect information games. Among these games, DouDizhu, a popular card game in China, is very challenging due to the imperfect information, large state space, elements of collaboration and a massive number of possible moves from turn to turn. Recently, a DouDizhu AI system called DouZero has been proposed. Trained using traditional Monte Carlo method with deep neural networks and self-play procedure without the abstraction of human prior knowledge, DouZero has outperformed all the existing DouDizhu AI programs. In this work, we propose to enhance DouZero by introducing opponent modeling into DouZero. Besides, we propose a novel coach network to further boost the performance of DouZero and accelerate its training process. With the integration of the above two techniques into DouZero, our DouDizhu AI system achieves better performance and ranks top in the Botzone leaderboard among more than 400 AI agents, including DouZero.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 18 of its 45 references that are in the map. First posted on arXiv 6 Apr 2022.

Builds on

18 of 45 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  3. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  4. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
  5. 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 228
  6. 2017Learning with Opponent-Learning Awarenesscited by 218
  7. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 153
  8. 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 150
  9. 2017Emergent Complexity via Multi-Agent Competitioncited by 117
  10. 2020Combining Deep Reinforcement Learning and Search for Imperfect-Information Gamescited by 110
  11. 2017A Deeper Look at Experience Replaycited by 104
  12. 2016Opponent Modeling in Deep Reinforcement Learningcited by 94
6 more
  1. 2018Learn What Not to Learn: Action Elimination with Deep Reinforcement Learningcited by 77
  2. 2021DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learningcited by 65
  3. 2020Suphx: Mastering Mahjong with Deep Reinforcement Learningcited by 55
  4. 2020Enhancing the Monte Carlo Tree Search Algorithm for Video Game Testingcited by 4
  5. 2021Improving Model and Search for Computer Gocited by 3
  6. 2018Monte Carlo Methods for the Game Kingdominocited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 5.

7 papers.

  1. 2024A Survey on Self-play Methods in Reinforcement Learningcited by 26
  2. 2024Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignmentcited by 7
  3. 2023DanZero+: Dominating the GuanDan Game through Reinforcement Learningcited by 6
  4. 2022DanZero: Mastering GuanDan Game with Reinforcement Learningcited by 5
  5. 2024DouRN: Improving DouZero by Residual Neural Networkscited by 0
  6. 2024AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Biddingcited by 0
  7. 2024Improve Value Estimation of Q Function and Reshape Reward with Monte Carlo Tree Searchcited by 0