AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning

Daochen Zha, Jingru Xie, Wenye Ma, Sheng Zhang, Xiangru Lian, Xia Hu, Ji Liu

ICML 2021 · Multi-agent systems and games › Games and equilibria · approach: Opponent modeling in competitive games · 21 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use DouZero's self-play reinforcement learning instead of supervised learning from expert matchesDouDizhu agents with the same neural architecture · DouDizhu vs SLWP: 0.341 -> 0.659Improved
Use DouZero's Deep Monte-Carlo learning instead of DeltaDou's search-based approachDouDizhu agents · 10,000-deck tournament vs DeltaDouWP: 0.414 -> 0.586Improved
Train the card-playing policy without bidding in the learning loop, then evaluate it with a shared bidding networkDouZero · 100,000-deck tournament with biddingWP: 0.461 -> 0.580 vs DeltaDouImproved
Replace Deep Monte-Carlo returns with a Temporal-Difference objective (ablation)DouZero · DouDizhu vs SLWPNo clear effect
Replace Deep Monte-Carlo with an actor-critic using action features in the critic and masks in the actor (ablation)DouZero · DouDizhu vs SLWPHurt
Increase the number of parallel actors from 15 to 30 or 45 (ablation)DouZero training · Training time against SLWPImproved
Use WP rather than ADP as the training reward (ablation)DouZero · DouDizhu tournamentsWPImproved
Use ADP rather than WP as the training reward (ablation)DouZero · DouDizhu tournamentsADPImproved
Continue self-play training beyond five daysDouZero · Human expert dataaccuracyHurt

Later papers that compared with this method

1 later accepted paper reports DouZero as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy