Unsupervised Reinforcement Learning on DMC (DeepMind Control Suite) Maze
11.22Entropy H(Mπ_S)
Soft FB_flow
Updated 4d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.02 | 11.22 | 15.54 | -5.25 | -1.39 | -5.07 | -2.51 | |
2026.02 | 10.83 | 10.52 | -6.49 | -6.45 | -6.57 | -7.27 |
Soft FB_flow
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.02 | 11.22 | 15.54 | -5.25 | -1.39 | -5.07 | -2.51 | |
2026.02 | 10.83 | 10.52 | -6.49 | -6.45 | -6.57 | -7.27 |