State Prediction on TD-MPC2 Reacher
0.0005MSEMoSim
Evaluation Results
| Method | Links | |
|---|---|---|
| MoSimTraining Data Source=random policy data, Horizon=162025.04 | 0.0005 | |
| MoSimTraining Data Source=random policy data, Horizon=1002025.04 | 0.0008 | |
| MoSimTraining Data Source=experience data, Horizon=162025.04 | 0.0027 | |
| MoSimTraining Data Source=experience data, Horizon=1002025.04 | 0.003 | |
| DreamerV3Training Data Source=random policy data, Prediction Steps=5-step, Horizon=162025.04 | 0.0488 | |
| DreamerV3Training Data Source=experience data, Prediction Steps=5-step, Horizon=162025.04 | 0.0514 | |
| DreamerV3Training Data Source=random policy data, Prediction Steps=5-step, Horizon=1002025.04 | 0.0571 | |
| DreamerV3Training Data Source=experience data, Prediction Steps=5-step, Horizon=1002025.04 | 0.0803 | |
| DreamerV3Training Data Source=experience data, Prediction Steps=1-step, Horizon=162025.04 | 0.343 | |
| DreamerV3Training Data Source=experience data, Prediction Steps=1-step, Horizon=1002025.04 | 0.3562 | |
| DreamerV3Training Data Source=random policy data, Prediction Steps=1-step, Horizon=1002025.04 | 0.4364 | |
| DreamerV3Training Data Source=random policy data, Prediction Steps=1-step, Horizon=162025.04 | 0.467 |