AI Paper Atlas

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

No-Press Diplomacy from Scratch

Anton Bakhtin, David J Wu, Adam Lerer, Noam Brown

NeurIPS 2021 · Multi-agent systems and games › Games and equilibria · approach: Opponent modeling in competitive games · 0 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
replace GraphConv encoder with TransformerEnc 5x192 (ablation)DORA · FvAfinal Elo: 898 -> 1041Improved
enlarge transformer from 5x192 to 10x224 (ablation)DORA · FvAfinal Elo: 1041 -> 1061Improved
use separate value and policy networks (ablation)DORA TransformerEnc 10x224 · FvAfinal Elo: 1061 -> 1123Improved
add DO with uniform random sampling during training (ablation)DORA · FvAfinal Elo: 927 -> 956Improved
add DO with local modification sampling during training (ablation)DORA · FvAfinal Elo: 927 -> 1023Improved
local modification instead of uniform random sampling in training DO (ablation)DORA · FvAfinal Elo: 956 -> 1023Improved
add inference-time DO with uniform random sampling (ablation)DORA Model1/2/3 · FvAaverage score vs same model: 0.75, 0.48, 0.47 vs 0.5Mixed
add inference-time DO with local modification sampling (ablation)DORA Model1/2/3 · FvAaverage score vs same model: 0.89, 0.59, 0.56 vs 0.5Improved
train exploiter with deep Nash method instead of actor-critic PGexploiter vs DORA · FvAexploiter win rate: 77.0% -> 90.5%Improved
disable policy learning in exploiter (values only) (ablation)Deep Nash-Derived Exploiter · FvAexploiter win rate vs DORA: 90.5% -> 65.7%Hurt
apply inference-time DO to DORADORA · FvAexploitability (exploiter win rate): 90.5% -> 85.8%Improved
start deep Nash value iteration from human-initialized policy with no proposal updateHumanDNVI-NPU · 7p no-press 1x vs 6x SearchBotSoS score: 11.0% -> 36.3%Improved

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