Offline-to-online Reinforcement Learning on hopper
353RegretSMAC
Evaluation results
| Method | Links | |
|---|---|---|
| SMACOffline Algorithm=SMAC, Fine-tuning algorithm=AWR2026.02 | 353 | |
| SMACFine-tuning algorithm=TD3+BC, Offline Algorithm=SMAC2026.02 | 425.5 | |
| CalQL/CQLOffline Algorithm=CalQL/CQL, Fine-tuning algorithm=AWR2026.02 | 533.7 | |
| TD3+BCOffline Algorithm=TD3+BC, Fine-tuning algorithm=AWR2026.02 | 552.4 | |
| IQLOffline Algorithm=IQL, Fine-tuning algorithm=AWR2026.02 | 958 | |
| TD3+BCFine-tuning algorithm=TD3+BC, Offline Algorithm=TD3+BC2026.02 | 1,295.4 | |
| IQLFine-tuning algorithm=TD3+BC, Offline Algorithm=IQL2026.02 | 1,392.6 | |
| CalQL/CQLFine-tuning algorithm=TD3+BC, Offline Algorithm=CalQL/CQL2026.02 | 2,469.9 |