Locomotion on D4RL Hopper-medium v2
113.22Online Normalized ReturnROID
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ROIDseeds=3, evaluation_rollouts=10, step_interval=50002026.05 | 113.22 | 51.21 | |
| BOORLevaluation_rollouts=10, step_interval=50002026.05 | 109.8 | 61.9 | |
| RLPDevaluation_rollouts=10, step_interval=50002026.05 | 107.3 | — | |
| Cal-QLevaluation_rollouts=10, step_interval=50002026.05 | 100.6 | 75.8 | |
| ODTevaluation_rollouts=10, step_interval=50002026.05 | 97.5 | 66.9 | |
| DUALTime steps=1M, Number of random seeds=52026.05 | 88.23 | — | |
| DACERTime steps=1M, Number of random seeds=52026.05 | 83.05 | — | |
| Diff-QLTime steps=1M, Number of random seeds=52026.05 | 80.26 | — | |
| PEXevaluation_rollouts=10, step_interval=50002026.05 | 78.6 | 63.8 | |
| DiffuserTime steps=1M, Number of random seeds=52026.05 | 70.43 | — | |
| EDISTime steps=1M, Number of random seeds=52026.05 | 68.9 | — | |
| IQLTime steps=1M, Number of random seeds=52026.05 | 66.61 | — |