Reinforcement Learning on DeepMind Control Quadruped Run
345,000Steps to 75% ReturnMind Dreamer
Evaluation Results
| Method | Links | |
|---|---|---|
| Mind DreamerHorizon=152026.05 | 345,000 | |
| Mind DreamerHorizon=52026.05 | 465,000 | |
| Mind DreamerHorizon=102026.05 | 585,500 | |
| Dreamer V32026.05 | 777,100 |