AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Model-Based Opponent Modeling

XiaoPeng Yu, Jiechuan Jiang, Wanpeng Zhang, Haobin Jiang, Zongqing Lu

NeurIPS 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: World-model-based agents · 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
Use MBOM instead of the strongest baseline, Meta-MAPGagent policy · Triangle Game, fixed policyscore: -2.01 ± 0.06 -> -1.19 ± 0.03Improved
Use MBOM instead of the strongest baseline, Meta-MAPGagent policy · Triangle Game, naïve learnerscore: -5.76 ± 0.29 -> -1.66 ± 0.29Improved
Use MBOM instead of the strongest baseline, Meta-MAPGagent policy · Triangle Game, reasoning learnerscore: -6.14 ± 0.84 -> -2.75 ± 0.89Improved
Use MBOM instead of the strongest baseline, Meta-MAPGagent policy · One-on-One, fixed policywin rate (%): 44.4 ± 1.5 -> 59.5 ± 0.9Improved
Use MBOM instead of the strongest baseline, Meta-MAPGagent policy · One-on-One, naïve learnerwin rate (%): 36.6 ± 1.6 -> 51.3 ± 1.0Improved
Use MBOM instead of the strongest baseline, Meta-MAPGagent policy · One-on-One, reasoning learnerwin rate (%): 31.1 ± 1.9 -> 64.2 ± 1.8Improved
Add recursive imagination rather than using level-0 opponent modeling alone (ablation)MBOM · Triangle Game and One-on-One, learning or reasoning opponentsperformanceImproved
Add recursive imagination rather than using level-0 opponent modeling alone (ablation)MBOM · Triangle Game and One-on-One, fixed-policy opponentsperformanceNo clear effect
Finetune IOPs with imagined best responses instead of random actions (ablation)MBOM · Triangle Game and One-on-One, reasoning learnersperformanceImproved
Add Bayesian mixing rather than use a single imagined policy (ablation)MBOM · Triangle Game and One-on-One, reasoning learnersperformanceImproved
Use Bayesian mixing instead of uniform mixing (ablation)MBOM · Triangle Game and One-on-OneperformanceImproved
Increase recursive-imagination levels from M=1 to M≥2 (ablation)MBOM · Triangle Game and One-on-OneperformanceImproved

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