Reinforcement Learning on DeepMind Control Suite Walker Stand (Steps to 75% Return)
120Steps to 75% ReturnMind Dreamer
Evaluation results
| Method | Links | |
|---|---|---|
| Mind DreamerHorizon=152026.05 | 120 | |
| Dreamer V32026.05 | 121.3 | |
| Mind DreamerHorizon=102026.05 | 147 | |
| Mind DreamerHorizon=52026.05 | 171.7 | |
| Plan2Explore2026.05 | 510 | |
| Dreamer V22026.05 | 546.7 |