Reinforcement Learning on DeepMind Control Cartpole Swingup
278,800Steps to 75% ReturnDreamer V3
Evaluation Results
| Method | Links | |
|---|---|---|
| Dreamer V32026.05 | 278,800 | |
| Mind DreamerHorizon=102026.05 | 309,200 | |
| Mind DreamerHorizon=152026.05 | 309,800 | |
| Mind DreamerHorizon=52026.05 | 360,500 | |
| Dreamer V22026.05 | 656,800 | |
| Plan2Explore2026.05 | 1,123,300 |