Multi-Agent Reinforcement Learning on MAMuJoCo Walker2d 6x1 (test)
1,116.75Average Episodic ReturnSim2O
Evaluation results
| Method | Links | |
|---|---|---|
| Sim2OSteps=1 million2026.06 | 1,116.75 | |
| PROTO-MASteps=1 million2026.06 | 1,062.81 | |
| PEX-MASteps=1 million2026.06 | 1,017.93 | |
| RLPD-MASteps=1 million2026.06 | 884.7 | |
| AWAC-MASteps=1 million2026.06 | 872.62 | |
| MMSA2026.02 | 28.56 | |
| QMIX2026.02 | 23.33 | |
| VDN2026.02 | 18.72 | |
| IQL2026.02 | 18.61 | |
| SMMAE2026.02 | 12.16 | |
| QMIX-CIA2026.02 | 10.86 | |
| MASER2026.02 | 7.4 | |
| QPLEX-CIA2026.02 | 6.56 |