Reinforcement Learning on DeepMind Control Cartpole Balance (Steps to 75% Return)
203,100Steps to 75% ReturnDreamer V3
Evaluation Results
| Method | Links | |
|---|---|---|
| Dreamer V32026.05 | 203,100 | |
| Mind DreamerHorizon=152026.05 | 239,600 | |
| Mind DreamerHorizon=102026.05 | 243,700 | |
| Mind DreamerHorizon=52026.05 | 266,800 | |
| Dreamer V22026.05 | 555,200 | |
| Plan2Explore2026.05 | 1,003,300 |