mlsanityData to 7 Oct 2026

PerfectDou: Dominating DouDizhu with Perfect Information Distillation

arXiv 2203.16406 ↗First posted 30 Mar 2022cs.AI cs.GT cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

As a challenging multi-player card game, DouDizhu has recently drawn much attention for analyzing competition and collaboration in imperfect-information games. In this paper, we propose PerfectDou, a state-of-the-art DouDizhu AI system that dominates the game, in an actor-critic framework with a proposed technique named perfect information distillation. In detail, we adopt a perfect-training-imperfect-execution framework that allows the agents to utilize the global information to guide the training of the policies as if it is a perfect information game and the trained policies can be used to play the imperfect information game during the actual gameplay. To this end, we characterize card and game features for DouDizhu to represent the perfect and imperfect information. To train our system, we adopt proximal policy optimization with generalized advantage estimation in a parallel training paradigm. In experiments we show how and why PerfectDou beats all existing AI programs, and achieves state-of-the-art performance.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 23 of its 43 references that are in the map. First posted on arXiv 30 Mar 2022.

Builds on

23 of 43 references.

References · 23

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  3. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  4. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  5. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 866
  6. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  7. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 561
  8. 2018Horovod: fast and easy distributed deep learning in TensorFlowcited by 275
  9. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
  10. 2017DeepStack: Expert-Level Artificial Intelligence in No-Limit Pokercited by 228
  11. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 153
  12. 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 150
11 more
  1. 2018Deep Counterfactual Regret Minimizationcited by 102
  2. 2021DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learningcited by 65
  3. 2020Suphx: Mastering Mahjong with Deep Reinforcement Learningcited by 55
  4. 2020DREAM: Deep Regret minimization with Advantage baselines and Model-free learningcited by 36
  5. 2018Actor-Critic Policy Optimization in Partially Observable Multiagent Environmentscited by 35
  6. 2019RLCard: A Toolkit for Reinforcement Learning in Card Gamescited by 34
  7. 2019Improving Policies via Search in Cooperative Partially Observable Gamescited by 33
  8. 2021Universal Trading for Order Execution with Oracle Policy Distillationcited by 29
  9. 2020The Advantage Regret-Matching Actor-Criticcited by 17
  10. 2014Solving Games with Functional Regret Estimationcited by 12
  11. 2019Combinational Q-Learning for Dou Di Zhucited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 5; 2024: 2; 2025: 2; 2026: 1.

15 papers.

Sort:

By area:

  1. 2022Bootstrapped Transformer for Offline Reinforcement Learningcited by 37
  2. 2024A Survey on Self-play Methods in Reinforcement Learningcited by 26
  3. 2022Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemblecited by 18
  4. 2023TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Playcited by 18
  5. 2023Visual Imitation Learning with Patch Rewardscited by 16
  6. 2022Reinforcement Learning with Automated Auxiliary Loss Searchcited by 12
  7. 2025Scalable Decision Making for Games of Imperfect Informationcited by 7
  8. 2023Is Risk-Sensitive Reinforcement Learning Properly Resolved?cited by 2
  9. 2023JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Gamescited by 2
  10. 2022Towards Modern Card Games with Large-Scale Action Spaces Through Action Representationcited by 1
  11. 2024Offline Fictitious Self-Play for Competitive Gamescited by 1
  12. 2025Mxplainer: Explain and Learn Insights by Imitating Mahjong Agentscited by 1
3 more
  1. 2022Planning Immediate Landmarks of Targets for Model-Free Skill Transfer across Agentscited by 0
  2. 2023Two-Step Reinforcement Learning for Multistage Strategy Card Gamecited by 0
  3. 2026GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learningcited by 0