Unsupervised Reinforcement Learning on DMC (DeepMind Control Suite) Cheetah
13.63Entropy H(Mπ_S)
Soft FB_flow
Updated 4d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.02 | 13.63 | 17.83 | -4.56 | -1.02 | -4.38 | -1.23 | |
2026.02 | 11.74 | 11.68 | -5.56 | -7.25 | -5.45 | -7.55 |
Soft FB_flow
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.02 | 13.63 | 17.83 | -4.56 | -1.02 | -4.38 | -1.23 | |
2026.02 | 11.74 | 11.68 | -5.56 | -7.25 | -5.45 | -7.55 |