Hopper Control on MuJoCo (eval)
1,620.1RewardC-T Baseline
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| C-T BaselineKnowledge Level=Zero Knowledge2025.04 | 1,620.1 | 284.2 | 6,000 | |
| TraCeSKnowledge Level=Zero Knowledge2025.04 | 1,610.7 | 17.1 | 2,993 | |
| RLSFKnowledge Level=Partial Knowledge2025.04 | 1,577.7 | 20.4 | 6,690 | |
| CPPO-PIDKnowledge Level=Oracle2025.04 | 1,357.3 | 12.7 | — | |
| PPO-LagrangianKnowledge Level=Oracle2025.04 | 1,046.1 | 29.1 | — |