Multi-agent Reinforcement Learning on MaMuJoCo OMIGA 2-Ant (Medium-Expert)
2,002Average Episode RewardOMSD
Evaluation Results
| Method | Links | |
|---|---|---|
| OMSD2025.05 | 2,002 | |
| OMIGA2025.05 | 1,720.33 | |
| Sim2OSteps=1 million2026.06 | 1,689.52 | |
| PEX-MASteps=1 million2026.06 | 1,650.58 | |
| RLPD-MASteps=1 million2026.06 | 1,605.23 | |
| ICQ2025.05 | 1,590.18 | |
| AWAC-MASteps=1 million2026.06 | 1,566.56 | |
| PROTO-MASteps=1 million2026.06 | 1,269.24 | |
| BCQMA2025.05 | 1,020.89 | |
| CQLMA2025.05 | 800.22 | |
| OMAR2025.05 | -2,992.8 |