AI Paper Atlas

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

An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination

Xue Yan, Jiaxian Guo, Xingzhou Lou, Jun Wang, Haifeng Zhang, Yali Du

NeurIPS 2023 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Human-AI coordination agents · 5 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 E3T (mixture partner + partner modeling) instead of self-playSP · Overcooked human proxyaverage reward: 65.8 ± 5.5 -> 114.1 ± 6.4Improved
Replace MEP population training with E3T end-to-endMEP · Overcooked human proxyaverage reward: 89.7 ± 7.1 -> 114.1 ± 6.4Improved
Replace MEP with E3T for training costMEP · Overcooked Cramped Rm.training time (h): 17.9 -> 1.9Improved
Add partner modeling module to self-play, E3T(+P) (ablation)SP · Overcooked AI-AI coordinationaverage rewardImproved
Add mixture partner policy to self-play, E3T(+R) (ablation)SP · Overcooked AI-AI coordinationaverage rewardMixed
Combine mixture partner and partner modeling, E3T(R+P) (ablation)E3T(+R), E3T(+P) · Overcooked AI-AI coordinationaverage reward over layoutsImproved
Vary balance parameter epsilon from 0.1 to 0.9 (ablation)E3T · Overcooked Coord. Ringaverage reward: optimal 0.3 and 0.5Mixed
Set epsilon to 0.0 instead of 0.5 (ablation)E3T · Overcooked Forced Coord.average rewardImproved
Use E3T with epsilon 0.0 (partner modeling only) instead of SP (ablation)SP · Overcooked Forced Coord.average rewardImproved
Raise epsilon from 0.0 to 0.5 (ablation)E3T · Overcooked Coord. Ringpartner action prediction accuracy: 40% -> 55%Improved
Add mixture partner policy to MAPPO self-playSelf-play · Google Football 3 vs 1 with Keeperzero-shot winning rate (mean): 0.07 ± 0.08 -> 0.49 ± 0.21Improved
Add mixture partner policy to MAPPO self-playSelf-play · Google Football 3 vs 1 with Keepertraining winning rate: 0.79 ± 0.08 -> 0.76 ± 0.09No clear effect

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