Continuous Control on DMControl GB (train)
872Cartpole Swingup ScoreDrQ
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DrQObservation mode=training2024.09 | 872 | 884 | 955 | 827 | 333 | |
| SRMObservation mode=training, Base algorithm=SAC2024.09 | 871 | 925 | 959 | 715 | 298 | |
| SMGObservation mode=training2024.09 | 858 | 961 | 964 | 924 | 357 | |
| SVEAObservation mode=training, variant=overlay2024.09 | 809 | 923 | 959 | 753 | 300 | |
| SGQNObservation mode=training2024.09 | 805 | 922 | 952 | 876 | 343 | |
| SODAObservation mode=training2024.09 | 687 | 801 | 881 | 581 | 225 | |
| SACObservation mode=training2024.09 | 186 | 306 | 630 | 422 | 311 |