mlsanityData to 7 Oct 2026

Suphx: Mastering Mahjong with Deep Reinforcement Learning

arXiv 2003.13590 ↗First posted 30 Mar 2020cs.AIcited by 55

Not on the map. Why?

Abstract (arXiv)

Artificial Intelligence (AI) has achieved great success in many domains, and game AI is widely regarded as its beachhead since the dawn of AI. In recent years, studies on game AI have gradually evolved from relatively simple environments (e.g., perfect-information games such as Go, chess, shogi or two-player imperfect-information games such as heads-up Texas hold'em) to more complex ones (e.g., multi-player imperfect-information games such as multi-player Texas hold'em and StartCraft II). Mahjong is a popular multi-player imperfect-information game worldwide but very challenging for AI research due to its complex playing/scoring rules and rich hidden information. We design an AI for Mahjong, named Suphx, based on deep reinforcement learning with some newly introduced techniques including global reward prediction, oracle guiding, and run-time policy adaptation. Suphx has demonstrated stronger performance than most top human players in terms of stable rank and is rated above 99.99% of all the officially ranked human players in the Tenhou platform. This is the first time that a computer program outperforms most top human players in Mahjong.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 12; 2023: 12; 2024: 9; 2025: 7; 2026: 8.

55 papers.

Sort:

By area:

  1. 2021DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learningcited by 65
  2. 2023Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learningcited by 45
  3. 2023What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?cited by 36
  4. 2021Universal Trading for Order Execution with Oracle Policy Distillationcited by 29
  5. 2024A Survey on Self-play Methods in Reinforcement Learningcited by 26
  6. 2022ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regretcited by 24
  7. 2022RetroGraph: Retrosynthetic Planning with Graph Searchcited by 23
  8. 2022Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemblecited by 18
  9. 2022PerfectDou: Dominating DouDizhu with Perfect Information Distillationcited by 15
  10. 2024FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learningcited by 13
  11. 2024PUZZLES: A Benchmark for Neural Algorithmic Reasoningcited by 12
  12. 2025Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoningcited by 12
38 more
  1. 2022Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent RLcited by 11
  2. 2023Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Playcited by 10
  3. 2023Mastering Strategy Card Game (Hearthstone) with Improved Techniquescited by 10
  4. 2023Bridging the Sim-to-Real Gap from the Information Bottleneck Perspectivecited by 8
  5. 2022DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learningcited by 7
  6. 2025PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learningcited by 7
  7. 2023DanZero+: Dominating the GuanDan Game through Reinforcement Learningcited by 6
  8. 2024UNO Arena for Evaluating Sequential Decision-Making Capability of Large Language Modelscited by 6
  9. 2022DanZero: Mastering GuanDan Game with Reinforcement Learningcited by 5
  10. 2022Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolboxcited by 4
  11. 2025Can Large Language Models Master Complex Card Games?cited by 4
  12. 2023A survey on algorithms for Nash equilibria in finite normal-form gamescited by 3
  13. 2021Goal-Directed Planning by Reinforcement Learning and Active Inferencecited by 2
  14. 2023JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Gamescited by 2
  15. 2024RL-LLM-DT: An Automatic Decision Tree Generation Method Based on RL Evaluation and LLM Enhancementcited by 2
  16. 2021AI in Human-computer Gaming: Techniques, Challenges and Opportunitiescited by 1
  17. 2022Building a 3-Player Mahjong AI using Deep Reinforcement Learningcited by 1
  18. 2022Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learningcited by 1
  19. 2022Towards Modern Card Games with Large-Scale Action Spaces Through Action Representationcited by 1
  20. 2023Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIscited by 1
  21. 2024Mastering the Game of Guandan with Deep Reinforcement Learning and Behavior Regulatingcited by 1
  22. 2025Mxplainer: Explain and Learn Insights by Imitating Mahjong Agentscited by 1
  23. 2025Real-World Reinforcement Learning of Active Perception Behaviorscited by 1
  24. 2026Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Gamescited by 1
  25. 2021ScrofaZero: Mastering Trick-taking Poker Game Gongzhu by Deep Reinforcement Learningcited by 0
  26. 2021A Fast Algorithm for Computing the Deficiency Number of a Mahjong Handcited by 0
  27. 2021On the complexity of Dark Chinese Chesscited by 0
  28. 2022Classifying Ambiguous Identities in Hidden-Role Stochastic Games with Multi-Agent Reinforcement Learningcited by 0
  29. 2023Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learningcited by 0
  30. 2023Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbationscited by 0
  31. 2023Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Playcited by 0
  32. 2024Securing Equal Share: A Principled Approach for Learning Multiplayer Symmetric Gamescited by 0
  33. 2024A Simple, Solid, and Reproducible Baseline for Bridge Bidding AIcited by 0
  34. 2024AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Biddingcited by 0
  35. 2025Mastering Da Vinci Code: A Comparative Study of Transformer, LLM, and PPO-based Agentscited by 0
  36. 2025Oracle-Guided Masked Contrastive Reinforcement Learning for Visuomotor Policiescited by 0
  37. 2026Adapting Rules of Official International Mahjong for Online Playerscited by 0
  38. 2026Learning Provably Correct Distributed Protocols Without Human Knowledgecited by 0

50 most cited of 55 All 55 (JSON)