Continuous Control on MuJoCo Walker2d v5
5,626Max Average ReturnSAVGO
Evaluation results
| Method | Links | |
|---|---|---|
| SAVGOTraining steps=1,000,000, Seeds=102026.05 | 5,626 | |
| FMEREnvironment steps=1M, Random seeds=52026.03 | 5,285.08 | |
| DIPOEnvironment steps=1M, Random seeds=52026.03 | 5,028.66 | |
| TD3Environment steps=1M, Random seeds=52026.03 | 4,969.19 | |
| TQCTraining steps=1,000,000, Seeds=102026.05 | 4,952 | |
| DPMDEnvironment steps=1M, Random seeds=52026.03 | 4,910.31 | |
| QVPOEnvironment steps=1M, Random seeds=52026.03 | 4,846.39 | |
| SACTraining steps=1,000,000, Seeds=102026.05 | 4,693 | |
| PPOEnvironment steps=1M, Random seeds=52026.03 | 4,606.76 | |
| TD3Training steps=1,000,000, Seeds=102026.05 | 4,503 | |
| SACEnvironment steps=1M, Random seeds=52026.03 | 4,453.24 | |
| PPOTraining steps=1,000,000, Seeds=102026.05 | 4,321 | |
| FPOEnvironment steps=1M, Random seeds=52026.03 | 635.33 |