AI Paper Atlas

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

PerfectDou: Dominating DouDizhu with Perfect Information Distillation

Guan Yang, Minghuan Liu, Weijun Hong, Weinan Zhang, Fei Fang, Guangjun Zeng, Yue Lin

NeurIPS 2022 · Multi-agent systems and games › Games and equilibria · approach: Opponent modeling in competitive games · 14 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
train value function with perfect-information features (distillation) instead of imperfect-only (ablation)PerfectDou (1e9) · DouDizhu vs DouZero 1e10WP / ADP: WP 0.486 -> 0.524; ADP -0.057 -> 0.014Improved
add node-level perfect reward (ablation)PerfectDou (1e9) · DouDizhu vs DouZero 1e9ADP: 0.490 -> 1.270Improved
add node-level perfect reward (ablation)PerfectDou (1e9) · DouDizhu vs DouZero 1e9WP: 0.738 -> 0.732No clear effect
add perfect value features and node reward to vanilla PPO (ablation)PPO actor-critic · DouDizhu vs DouZero 1e9WP: 0.509 -> 0.732Improved
use PerfectDou's imperfect features in DouZero (ablation)DouZero · DouDizhu vs PerfectDouperformanceNo clear effect
PerfectDou 1e9 steps vs DouZero ~1e10 stepsPerfectDou · DouDizhu 100k decksWP: 0.524 vs 0.5 baseline; ADP 0.014Improved
train longer: 1e9 to 2.5e9 stepsPerfectDou · DouDizhu vs DouZero ~1e10ADP: 0.014 -> 0.130Improved

Later papers that compared with this method

1 later accepted paper reports PerfectDou 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