Multi-agent Reinforcement Learning on MaMuJoCo OMIGA 6-HalfCheetah (Medium-Replay)
4,582Avg Episode RewardOMSD
Evaluation Results
| Method | Links | |
|---|---|---|
| OMSD2025.05 | 4,582 | |
| Sim2OSteps=1 million2026.06 | 3,145.98 | |
| PEX-MASteps=1 million2026.06 | 2,850.57 | |
| AWAC-MASteps=1 million2026.06 | 2,550.09 | |
| OMIGA2025.05 | 2,504.7 | |
| RLPD-MASteps=1 million2026.06 | 2,488.39 | |
| PROTO-MASteps=1 million2026.06 | 2,327.58 | |
| CQLMA2025.05 | 1,998.67 | |
| ICQ2025.05 | 1,922.42 | |
| OMAR2025.05 | -235.42 | |
| BCQMA2025.05 | -333.64 |