Methods › Reinforcement Learning › Card Game Models › DouZero
DouZero
Introduced by Daochen Zha et al. in DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
DouZero is an AI system for the card game DouDizhu that enhances traditional Monte-Carlo methods with deep neural networks, action encoding, and parallel actors. The Q-network of DouZero consists of an LSTM to encode historical actions and six layers of MLP with hidden dimension of 512. The network predicts a value for a given state-action pair based on the concatenated representation of action and state.
Papers archive 2025-07-28
4 shown of 4, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Bidding 14 Jul 2024 · 1 repository · arXiv:2407.10279
-
DouRN: Improving DouZero by Residual Neural Networks 21 Mar 2024 · 0 repositories · arXiv:2403.14102
-
DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning 6 Apr 2022 · 1 repository · arXiv:2204.02558
-
DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning 11 Jun 2021 · 1 repository · arXiv:2106.06135Syntology ran 3 of 6 samples · 3 unverified · 1 pointer-only (licence)
Tasks archive 2025-07-28
7 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Deep Reinforcement Learning | 3 |
| Card Games | 2 |
| Game of Poker | 1 |
| Multi-agent Reinforcement Learning | 1 |
| Reinforcement Learning | 1 |
| Reinforcement Learning (RL) | 1 |
| reinforcement-learning | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections