Physical State Prediction on DeepMind Control Suite Cheetah Easy tasks (random policy)
0.1206MSEMoSim
Evaluation results
| Method | Links | |
|---|---|---|
| MoSimHorizon=16, Training data source=random policy data2025.04 | 0.1206 | |
| DreamerV3Horizon=16, Prediction steps=5-step, Training data source=random policy data2025.04 | 0.1925 | |
| MoSimHorizon=100, Training data source=random policy data2025.04 | 0.2185 | |
| DreamerV3Horizon=100, Prediction steps=5-step, Training data source=random policy data2025.04 | 0.2297 | |
| DreamerV3Horizon=100, Prediction steps=1-step, Training data source=random policy data2025.04 | 0.4048 | |
| MoSimHorizon=16, Training data source=experience data2025.04 | 0.5342 | |
| DreamerV3Horizon=16, Prediction steps=1-step, Training data source=random policy data2025.04 | 0.8747 | |
| MoSimHorizon=100, Training data source=experience data2025.04 | 1.1876 | |
| DreamerV3Horizon=100, Prediction steps=5-step, Training data source=experience data2025.04 | 5.8468 | |
| DreamerV3Horizon=16, Prediction steps=5-step, Training data source=experience data2025.04 | 6.527 | |
| DreamerV3Horizon=100, Prediction steps=1-step, Training data source=experience data2025.04 | 6.5507 | |
| DreamerV3Horizon=16, Prediction steps=1-step, Training data source=experience data2025.04 | 8.2538 |