AI Paper Atlas

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

Human-Level Performance in No-Press Diplomacy via Equilibrium Search

Jonathan Gray, Adam Lerer, Anton Bakhtin, Noam Brown

ICLR 2021 · Multi-agent systems and games › Games and equilibria · approach: Cooperation and social dilemmas · 9 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
add one-step regret-minimization equilibrium search to the human-trained blueprintBlueprint in no-press Diplomacy · 1v6 vs. BlueprintSoS score: 20.2% ± 1.3% -> 52.7% ± 1.3%Improved
add one-step regret-minimization equilibrium searchBlueprint in no-press Diplomacy · 1 expert human vs. 6 botshuman SoS score: 22.5% -> 5.7%Improved
add imitation-learning model improvementsDipNet blueprint · 1 expert human vs. 6 botshuman SoS score: 39.1% -> 22.5%Improved
add combined build-order modeling and encoder dropout (ablation)DipNet imitation model · Policy accuracyaccuracy: 60.5% -> 62.0%Improved
add encoder changes from prior work (ablation)DipNet imitation model · Policy accuracyaccuracy: 62.0% -> 62.4%Improved
use webdiplomacy training data only (ablation)Imitation-learning blueprint · Policy accuracyaccuracy: 62.4% -> 61.3%Hurt
add output featurization (ablation)Blueprint trained on webdiplomacy data · Policy accuracyaccuracy: 61.3% -> 62.0%Improved
add output featurization (ablation)Blueprint trained on webdiplomacy data · SoS vs. DipNet, temp=0.1SoS score: 0.206 -> 0.188Hurt
add the improved GNN layer (ablation)Blueprint trained on webdiplomacy data · Policy accuracyaccuracy: 61.3% -> 62.4%Improved
add the merged GNN trunk (ablation)Blueprint trained on webdiplomacy data · Policy accuracyaccuracy: 61.3% -> 62.9%Improved
average final-iteration RM policies across random seeds instead of using one run's final policy (ablation)Regret-matching search · Subgame 1exploitability: 0.00880 -> 0.00038Improved
average final-iteration RM policies across random seeds instead of using one run's final policy (ablation)Regret-matching search · Subgame 2exploitability: 0.0580 -> 0.0077Improved

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