Continuous Control on MuJoCo Walker2d
5,026.85Max ReturnCrossQ+FEMA
Evaluation Results
| Method | Links | |
|---|---|---|
| CrossQ+FEMAintegration=FEMA2026.03 | 5,026.85 | |
| SAC+FEMAintegration=FEMA2026.03 | 4,728.77 | |
| CrossQ2026.03 | 4,580.71 | |
| PPO+FEMAintegration=FEMA2026.03 | 4,538.86 | |
| EMAC2026.03 | 4,538.35 | |
| SAC2026.03 | 4,102.53 | |
| PPO2026.03 | 4,004.54 | |
| AGD-MBRLGuide=SAG2026.04 | 3,844.67 | |
| AGD-MBRLGuide=EAG2026.04 | 3,794.24 | |
| PolyGRADGuide=Diffuser Guide2026.04 | 3,777.73 | |
| PolyGRADGuide=None2026.04 | 3,489.48 | |
| TRPO2026.04 | 3,090.8 | |
| PPO2026.04 | 1,894.03 |