Reinforcement Learning on DeepMind Control Hopper Stand
245.2Steps to 75% Return (k)Mind Dreamer
Evaluation results
| Method | Links | |
|---|---|---|
| Mind DreamerHorizon=102026.05 | 245.2 | |
| Mind DreamerHorizon=152026.05 | 255.2 | |
| Mind DreamerHorizon=52026.05 | 333.4 | |
| Dreamer V32026.05 | 345.5 | |
| Dreamer V22026.05 | 730.6 |