Continuous Control on DeepMind Control Suite (train)
3.8acrobot-swingupTD-MPC2
Evaluation Results
| Method | Links | |||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| TD-MPC2maximum environment step budget=250K or 500K2025.12 | 3.8 | 2.6 | 1.2 | 1.9 | 2.3 | 2.8 | 1.9 | 2.9 | 2.7 | 2.6 | 3.8 | 2.3 | 5 | 2.7 | 3.7 | 3.9 | 1.8 | 3.7 | 1.3 | |
| Dreamer v3maximum environment step budget=250K or 500K2025.12 | 2.9 | 2.9 | 1.5 | 2.9 | 2.9 | 4.1 | 1.6 | 3.2 | 3.2 | 3.2 | 3.1 | 3.3 | 2.9 | 3.2 | 2.9 | 3.2 | 1.6 | 1.5 | 1.3 | |
| DHMBPOmaximum environment step budget=250K or 500K2025.12 | 1.7 | 1.6 | 0.9 | 0.9 | 1.9 | 2.7 | 1.2 | 2.2 | 2.2 | 2.2 | 2.7 | 3.2 | 4.3 | 3.7 | 2 | 2.7 | 1.2 | 1.7 | 1 |