Unsupervised Reinforcement Learning on DMC (DeepMind Control Suite) Walker
13.97Entropy (State-Dependent Policy)Soft FB_flow
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Soft FB_flowZero-shot=true, Average over seeds=52026.02 | 13.97 | 18.01 | -5.25 | -1.48 | -5.69 | -1.53 | |
| FB_flowZero-shot=true, Average over seeds=52026.02 | 12.56 | 9.86 | -5.35 | -9.4 | -5.69 | -9.43 |