Continuous Control on MuJoCo Humanoid v5
7,687Maximum Average ReturnSAVGO
Evaluation results
| Method | Links | |
|---|---|---|
| SAVGOTraining steps=1,000,000, Seeds=102026.05 | 7,687 | |
| TQCTraining steps=1,000,000, Seeds=102026.05 | 6,330 | |
| SACTraining steps=1,000,000, Seeds=102026.05 | 5,351 | |
| SACEnvironment steps=1M, Random seeds=52026.03 | 5,350.96 | |
| FMEREnvironment steps=1M, Random seeds=52026.03 | 5,286.12 | |
| DIPOEnvironment steps=1M, Random seeds=52026.03 | 5,123.38 | |
| DPMDEnvironment steps=1M, Random seeds=52026.03 | 5,100.6 | |
| QVPOEnvironment steps=1M, Random seeds=52026.03 | 5,078 | |
| PPOEnvironment steps=1M, Random seeds=52026.03 | 811.94 | |
| TD3Training steps=1,000,000, Seeds=102026.05 | 799 | |
| PPOTraining steps=1,000,000, Seeds=102026.05 | 554 | |
| FPOEnvironment steps=1M, Random seeds=52026.03 | 371.46 | |
| TD3Environment steps=1M, Random seeds=52026.03 | 363.16 |