Locomotion on MuJoCo halfcheetah-random
93.8Normalized ScoreCPQL→PQL
Evaluation Results
| Method | Links | |
|---|---|---|
| CPQL→PQLEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.05 | 93.8 | |
| RLPDEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.05 | 91.5 | |
| CQL→SACEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.05 | 90.3 | |
| PEXEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.05 | 60.9 | |
| Cal-QLEvaluation Protocol=Offline-to-Online, Online Samples=300k, Number of Seeds=52026.05 | 32.9 |