# DanZero: Mastering GuanDan Game with Reinforcement Learning

arXiv: https://arxiv.org/abs/2210.17087 · HTML: https://mlsanity.com/paper/2210.17087/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 40 references that are in the map.
- First posted on arXiv 31 Oct 2022.

## Builds on (most cited first, 15 of 15)

- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker](https://mlsanity.com/paper/1701.01724/) (2017)
- [Mastering Complex Control in MOBA Games with Deep Reinforcement Learning](https://mlsanity.com/paper/1912.09729/) (2019)
- [Deep Reinforcement Learning from Self-Play in Imperfect-Information Games](https://mlsanity.com/paper/1603.01121/) (2016)
- [Combining Deep Reinforcement Learning and Search for Imperfect-Information Games](https://mlsanity.com/paper/2007.13544/) (2020)
- [Deep Counterfactual Regret Minimization](https://mlsanity.com/paper/1811.00164/) (2018)
- [Opponent Modeling in Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05559/) (2016)
- [Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning](https://mlsanity.com/paper/1809.02121/) (2018)
- [DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning](https://mlsanity.com/paper/2106.06135/) (2021)
- [Suphx: Mastering Mahjong with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.13590/) (2020)
- [General Video Game AI: a Multi-Track Framework for Evaluating Agents, Games and Content Generation Algorithms](https://mlsanity.com/paper/1802.10363/) (2018)
- [Single Deep Counterfactual Regret Minimization](https://mlsanity.com/paper/1901.07621/) (2019)
- [Double Neural Counterfactual Regret Minimization](https://mlsanity.com/paper/1812.10607/) (2018)
- [DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning](https://mlsanity.com/paper/2204.02558/) (2022)

## Built on by (most cited first, 5 of 5)

- [Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information](https://mlsanity.com/paper/2408.02559/) (2024)
- [Games for Artificial Intelligence Research: A Review and Perspectives](https://mlsanity.com/paper/2304.13269/) (2023)
- [DanZero+: Dominating the GuanDan Game through Reinforcement Learning](https://mlsanity.com/paper/2312.02561/) (2023)
- [Can Large Language Models Master Complex Card Games?](https://mlsanity.com/paper/2509.01328/) (2025)
- [OpenGuanDan: A Large-Scale Imperfect Information Game Benchmark](https://mlsanity.com/paper/2602.00676/) (2026)

## Abstract (arXiv)

Card game AI has always been a hot topic in the research of artificial intelligence. In recent years, complex card games such as Mahjong, DouDizhu and Texas Hold'em have been solved and the corresponding AI programs have reached the level of human experts. In this paper, we are devoted to developing an AI program for a more complex card game, GuanDan, whose rules are similar to DouDizhu but much more complicated. To be specific, the characteristics of large state and action space, long length of one episode and the unsure number of players in the GuanDan pose great challenges for the development of the AI program. To address these issues, we propose the first AI program DanZero for GuanDan using reinforcement learning technique. Specifically, we utilize a distributed framework to train our AI system. In the actor processes, we carefully design the state features and agents generate samples by self-play. In the learner process, the model is updated by Deep Monte-Carlo Method. After training for 30 days using 160 CPUs and 1 GPU, we get our DanZero bot. We compare it with 8 baseline AI programs which are based on heuristic rules and the results reveal the outstanding performance of DanZero. We also test DanZero with human players and demonstrate its human-level performance.