Human-AI Coordination on Overcooked Asym. Adv.
198.18Mean RewardPASD
Evaluation results
| Method | Links | |
|---|---|---|
| PASDPartner type=Human participants, Horizon length=400, Training steps=10^7, Skill dimension (z)=6, Backbone=CNN + recurrent LSTM layer2026.05 | 198.18 | |
| IADPartner Type=Human2026.05 | 198 | |
| HiPTPartner type=Human participants, Horizon length=400, Training steps=10^7, Skill dimension (z)=6, Backbone=CNN + recurrent LSTM layer2026.05 | 136.36 | |
| HiPTPartner Type=Human2026.05 | 136 |