Multi-agent Reinforcement Learning on MaMuJoCo OMIGA 2-Ant (Medium)
1,798.05Average Episode RewardSim2O
Evaluation Results
| Method | Links | |
|---|---|---|
| Sim2OSteps=1 million2026.06 | 1,798.05 | |
| PEX-MASteps=1 million2026.06 | 1,733.31 | |
| OMSD2025.05 | 1,619 | |
| AWAC-MASteps=1 million2026.06 | 1,420.05 | |
| PROTO-MASteps=1 million2026.06 | 1,419.49 | |
| OMIGA2025.05 | 1,418.44 | |
| ICQ2025.05 | 1,412.41 | |
| RLPD-MASteps=1 million2026.06 | 1,407.25 | |
| BCQMA2025.05 | 1,059.6 | |
| CQLMA2025.05 | 533.9 | |
| OMAR2025.05 | -1,710.04 |