Reinforcement Learning on DeepMind Control Quadruped Walk
330,500Steps to Reach 75% ReturnMind Dreamer
Evaluation Results
| Method | Links | |
|---|---|---|
| Mind DreamerHorizon=52026.05 | 330,500 | |
| Mind DreamerHorizon=152026.05 | 335,000 | |
| Plan2Explore2026.05 | 573,300 | |
| Dreamer V32026.05 | 619,300 | |
| Mind DreamerHorizon=102026.05 | 684,900 | |
| Dreamer V22026.05 | 879,300 |