Continuous Control on MuJoCo Hopper v5
3,671.77Average ReturnQVPO
Evaluation results
| Method | Links | ||
|---|---|---|---|
| QVPOEnvironment steps=1M, Random seeds=52026.03 | 3,671.77 | — | |
| TD3Environment steps=1M, Random seeds=52026.03 | 3,664.3 | — | |
| DIPOEnvironment steps=1M, Random seeds=52026.03 | 3,592.82 | — | |
| DPMDEnvironment steps=1M, Random seeds=52026.03 | 3,503.62 | — | |
| FMEREnvironment steps=1M, Random seeds=52026.03 | 3,444.46 | — | |
| SACEnvironment steps=1M, Random seeds=52026.03 | 3,354.63 | — | |
| PPOEnvironment steps=1M, Random seeds=52026.03 | 1,223.19 | — | |
| FPOEnvironment steps=1M, Random seeds=52026.03 | 1,216.86 | — | |
| PPOTraining steps=1,000,000, Seeds=102026.05 | — | 3,527 | |
| SACTraining steps=1,000,000, Seeds=102026.05 | — | 3,371 | |
| SAVGOTraining steps=1,000,000, Seeds=102026.05 | — | 3,573 | |
| TD3Training steps=1,000,000, Seeds=102026.05 | — | 3,584 | |
| TQCTraining steps=1,000,000, Seeds=102026.05 | — | 3,571 |