mlsanityData to 14 Oct 2026

DanZero+: Dominating the GuanDan Game through Reinforcement Learning

arXiv 2312.02561 ↗First posted 5 Dec 2023cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

The utilization of artificial intelligence (AI) in card games has been a well-explored subject within AI research for an extensive period. Recent advancements have propelled AI programs to showcase expertise in intricate card games such as Mahjong, DouDizhu, and Texas Hold'em. In this work, we aim to develop an AI program for an exceptionally complex and popular card game called GuanDan. This game involves four players engaging in both competitive and cooperative play throughout a long process to upgrade their level, posing great challenges for AI due to its expansive state and action space, long episode length, and complex rules. Employing reinforcement learning techniques, specifically Deep Monte Carlo (DMC), and a distributed training framework, we first put forward an AI program named DanZero for this game. Evaluation against baseline AI programs based on heuristic rules highlights the outstanding performance of our bot. Besides, in order to further enhance the AI's capabilities, we apply policy-based reinforcement learning algorithm to GuanDan. To address the challenges arising from the huge action space, which will significantly impact the performance of policy-based algorithms, we adopt the pre-trained model to facilitate the training process and the achieved AI program manages to achieve a superior performance.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 19 of its 45 references that are in the map. First posted on arXiv 5 Dec 2023.

Builds on

19 of 45 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Trust Region Policy Optimizationcited by 2,580
  3. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  5. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  6. 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 233
  7. 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 161
  8. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 158
  9. 2020Combining Deep Reinforcement Learning and Search for Imperfect-Information Gamescited by 114
  10. 2018Deep Counterfactual Regret Minimizationcited by 103
  11. 2016Opponent Modeling in Deep Reinforcement Learningcited by 97
  12. 2018Learn What Not to Learn: Action Elimination with Deep Reinforcement Learningcited by 77
7 more
  1. 2018Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learningcited by 68
  2. 2021DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learningcited by 66
  3. 2020Suphx: Mastering Mahjong with Deep Reinforcement Learningcited by 58
  4. 2018General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithmscited by 45
  5. 2019Single Deep Counterfactual Regret Minimizationcited by 20
  6. 2022DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learningcited by 7
  7. 2022DanZero: Mastering GuanDan Game with Reinforcement Learningcited by 5

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Informationcited by 20
  2. 2024Enhancing Commentary Strategies for Imperfect Information Card Games: A Study of Large Language Models in Guandan Commentarycited by 3
  3. 2024RL-LLM-DT: An Automatic Decision Tree Generation Method Based on RL Evaluation and LLM Enhancementcited by 2
  4. 2024Mastering the Game of Guandan with Deep Reinforcement Learning and Behavior Regulatingcited by 1
  5. 2025Reinforcement Learning-based Threat Assessmentcited by 0
  6. 2025Eval-PPO: Building an Efficient Threat Evaluator Using Proximal Policy Optimizationcited by 0