Multi-agent Reinforcement Learning on MaMuJoCo OMIGA 6-HalfCheetah (Medium-Expert)
5,237Average Episode RewardOMSD
Evaluation Results
| Method | Links | |
|---|---|---|
| OMSD2025.05 | 5,237 | |
| Sim2OSteps=1 million2026.06 | 4,994.26 | |
| AWAC-MASteps=1 million2026.06 | 4,709.65 | |
| PEX-MASteps=1 million2026.06 | 4,010.15 | |
| BCQMA2025.05 | 3,543.7 | |
| PROTO-MASteps=1 million2026.06 | 3,367.27 | |
| RLPD-MASteps=1 million2026.06 | 3,026.93 | |
| OMIGA2025.05 | 2,948.46 | |
| ICQ2025.05 | 2,833.99 | |
| CQLMA2025.05 | 1,194.23 | |
| OMAR2025.05 | -253.84 |