Reinforcement Learning on DeepMind Control Finger Turn Hard (Steps to 75% Return)
333.4Steps to 75% ReturnDreamer V3
Evaluation Results
| Method | Links | |
|---|---|---|
| Dreamer V32026.05 | 333.4 | |
| Mind DreamerHorizon=102026.05 | 473.5 | |
| Mind DreamerHorizon=52026.05 | 514.9 | |
| Mind DreamerHorizon=152026.05 | 544.9 | |
| Dreamer V22026.05 | 763.5 | |
| Plan2Explore2026.05 | 1,293.3 |