Reinforcement Learning on DeepMind Control Reacher Hard (Convergence)
589.7Steps to 75% Return (k)Dreamer V3
Evaluation Results
| Method | Links | |
|---|---|---|
| Dreamer V32026.05 | 589.7 | |
| Dreamer V32026.05 | 698.2 | |
| Mind DreamerHorizon=102026.05 | 707 | |
| Mind DreamerHorizon=52026.05 | 804.9 | |
| Mind DreamerHorizon=152026.05 | 827.4 | |
| Mind DreamerHorizon=102026.05 | 967.8 | |
| Plan2Explore2026.05 | 1,196.7 | |
| Plan2Explore2026.05 | 1,516.7 |