AI Paper Atlas

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

Improving Policies via Search in Cooperative Partially Observable Games

Adam Lerer, Hengyuan Hu, Jakob Foerster, Noam Brown

AAAI 2020 · Multi-agent systems and games › Games and equilibria · approach: Opponent modeling in competitive games · 46 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 single-agent search to the agreed blueprintHanabi policies including SAD, SmartBot, CloneBot, and DQN · Hanabi 2-playeraverage score: 22.99 ± 0.001 -> 24.21 ± 0.002 (SmartBot); 24.08 ± 0.01 -> 24.53 ± 0.01 (SAD)Improved
Add retrospective multi-agent search after single-agent searchSmartBot, DQN, and SAD blueprints · Hanabi 2-playeraverage score: 24.21 ± 0.002 -> 24.46 ± 0.01 (SmartBot); 24.53 ± 0.01 -> 24.61 ± 0.01 (SAD)Improved
Add single-agent search to SADSAD · Hanabi 3-playeraverage score: 23.99 ± 0.01 -> 24.61 ± 0.01Improved
Add single-agent search to SADSAD · Hanabi 4-playeraverage score: 23.81 ± 0.01 -> 24.49 ± 0.01Improved
Add single-agent search to SADSAD · Hanabi 5-playeraverage score: 23.01 ± 0.01 -> 23.91 ± 0.01Improved
Increase the max range for retrospective multi-agent search (ablation)SmartBot · Hanabi 2-playeraverage score: 24.21 ± 0.002 -> 24.48 ± 0.01 (max range 0 -> 10,000)Improved
Increase the max range for retrospective multi-agent search (ablation)SmartBot · Hanabi 2-playerrollouts: 1.5 × 10^5 -> 1.8 × 10^8 (max range 0 -> 10,000)Hurt
Use independent multi-agent search instead of coordinated retrospective search (ablation)SmartBot · Hanabi 2-playeraverage score: 22.99 -> 14.41Hurt
Raise the deviation threshold from 0 to 0.2 for independent search with belief uncertainty 0.05 (ablation)SmartBot · Hanabi 2-playeraverage score: 14.41 -> 24.18Improved
Use a deviation threshold of 0.05 rather than allowing all estimated improvements (ablation)SmartBot search · Hanabiaverage score: nullImproved
Use UCB-like pruning to skip rollouts for clearly inferior actions (ablation)SPARTA search · Hanabiaverage score: nullNo clear effect
Use UCB-like pruning and the blueprint deviation threshold (ablation)SPARTA search · Hanabirollouts per timestep: 10× fewer rolloutsImproved

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