Offline-to-online Reinforcement Learning on kitchen
256.6RegretCalQL/CQL
Evaluation results
| Method | Links | |
|---|---|---|
| CalQL/CQLFine-tuning algorithm=TD3+BC, Offline Algorithm=CalQL/CQL2026.02 | 256.6 | |
| SMACFine-tuning algorithm=TD3+BC, Offline Algorithm=SMAC2026.02 | 262.2 | |
| SMACOffline Algorithm=SMAC, Fine-tuning algorithm=AWR2026.02 | 340.6 | |
| CalQL/CQLOffline Algorithm=CalQL/CQL, Fine-tuning algorithm=AWR2026.02 | 343.7 | |
| TD3+BCFine-tuning algorithm=TD3+BC, Offline Algorithm=TD3+BC2026.02 | 373.4 | |
| IQLFine-tuning algorithm=TD3+BC, Offline Algorithm=IQL2026.02 | 385.2 | |
| IQLOffline Algorithm=IQL, Fine-tuning algorithm=AWR2026.02 | 446.4 | |
| TD3+BCOffline Algorithm=TD3+BC, Fine-tuning algorithm=AWR2026.02 | 837 |