Reinforcement Learning on DeepMind Control Walker Walk
116.8Steps to 75% ReturnMind Dreamer
Evaluation results
| Method | Links | |
|---|---|---|
| Mind DreamerHorizon=152026.05 | 116.8 | |
| Mind DreamerHorizon=52026.05 | 164.5 | |
| Dreamer V32026.05 | 167.6 | |
| Mind DreamerHorizon=102026.05 | 184.9 | |
| Dreamer V22026.05 | 446.9 | |
| Plan2Explore2026.05 | 490 |