Locomotion on ANYmal locomotion environment
100Success Rate (SR)DSRL
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| DSRLFine-tuning=Standard2026.05 | 100 | 25 | 1 | 0 | |
| DPPOReference=[10]2026.05 | 100 | 42 | 1.67 | 15 | |
| DSRLRegularization=ENTROPY2026.05 | 100 | 25 | 1 | 0 | |
| DSRLRegularization=RND2026.05 | 100 | 25 | 1 | 0 | |
| DPPOFine-tuning=Standard2026.05 | 99 | 32 | 1.33 | 9 | |
| RESFine-tuning=Standard2026.05 | 98 | 90 | 3.67 | 90 | |
| DSRLRegularization=BMD2026.05 | 97 | 89 | 3.67 | 91 | |
| PREstatus=Pre-trained2026.05 | 41 | 39 | 0 | 96 |