Multi-Agent Reinforcement Learning on Overcooked coord-ring JaxMARL implementation
218.5ReturnIPPO + FIM
Evaluation Results
| Method | Links | |
|---|---|---|
| IPPO + FIMalpha=1, phi=0.052025.06 | 218.5 | |
| IPPO2025.06 | 195.7 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| IPPO + FIMalpha=1, phi=0.052025.06 | 218.5 | |
| IPPO2025.06 | 195.7 |