Reinforcement Learning on DeepMind Control Cartpole Balance Sparse
150,700Steps to 75% ReturnDreamer V3
Evaluation Results
| Method | Links | |
|---|---|---|
| Dreamer V32026.05 | 150,700 | |
| Mind DreamerHorizon=102026.05 | 158,300 | |
| Mind DreamerHorizon=102026.05 | 166,300 | |
| Mind DreamerHorizon=52026.05 | 166,700 | |
| Dreamer V32026.05 | 170,400 | |
| Mind DreamerHorizon=152026.05 | 171,300 | |
| Mind DreamerHorizon=52026.05 | 174,400 | |
| Mind DreamerHorizon=152026.05 | 178,500 | |
| Dreamer V22026.05 | 345,000 | |
| Dreamer V22026.05 | 381,700 | |
| Plan2Explore2026.05 | 896,700 |