Continuous Control on MuJoCo Humanoid
6,969.74Average RewardCrossQ+FEMA
Evaluation Results
| Method | Links | |
|---|---|---|
| CrossQ+FEMAintegration=FEMA2026.03 | 6,969.74 | |
| CrossQ2026.03 | 6,267.3 | |
| TOP-TD3Training steps=1M, Number of trials=102021.02 | 5,899 | |
| ND TOP-TD3Training steps=1M, Number of trials=102021.02 | 5,445 | |
| SAC+FEMAintegration=FEMA2026.03 | 5,429.08 | |
| TD3Training steps=1M, Number of trials=102021.02 | 5,386 | |
| OACTraining steps=1M, Number of trials=102021.02 | 5,349 | |
| SACTraining steps=1M, Number of trials=102021.02 | 5,315 | |
| SAC2026.03 | 5,290.8 | |
| QR-TD3Training steps=1M, Number of trials=102021.02 | 5,003 | |
| EMAC2026.03 | 3,808.84 | |
| PPO+FEMAintegration=FEMA2026.03 | 1,102.82 | |
| PPO2026.03 | 902.71 |