Reinforcement Learning on DeepMind Control Cartpole Swingup Sparse
383,100Environment Steps to 75% ReturnMind Dreamer
Evaluation Results
| Method | Links | |
|---|---|---|
| Mind DreamerHorizon=152026.05 | 383,100 | |
| Mind DreamerHorizon=102026.05 | 385,900 | |
| Dreamer V32026.05 | 573,600 | |
| Dreamer V22026.05 | 636,900 | |
| Mind DreamerHorizon=52026.05 | 750,200 |