Physical state prediction on DeepMind Control Suite Panda Easy tasks (random policy)
0.001MSEMoSim
Evaluation results
| Method | Links | |
|---|---|---|
| MoSimHorizon=16, Training data source=random policy data2025.04 | 0.001 | |
| MoSimHorizon=100, Training data source=random policy data2025.04 | 0.0043 | |
| DreamerV3Horizon=16, Prediction steps=5-step, Training data source=random policy data2025.04 | 0.0434 | |
| DreamerV3Horizon=100, Prediction steps=5-step, Training data source=random policy data2025.04 | 0.0971 | |
| DreamerV3Horizon=16, Prediction steps=1-step, Training data source=random policy data2025.04 | 0.2396 | |
| DreamerV3Horizon=100, Prediction steps=1-step, Training data source=random policy data2025.04 | 0.3367 |