Offline-to-online Reinforcement Learning on door
50.3RegretSMAC
Evaluation results
| Method | Links | |
|---|---|---|
| SMACOffline Algorithm=SMAC, Fine-tuning algorithm=SAC2026.02 | 50.3 | |
| SMACFine-tuning algorithm=TD3+BC, Offline Algorithm=SMAC2026.02 | 72.3 | |
| IQLOffline Algorithm=IQL, Fine-tuning algorithm=SAC2026.02 | 120 | |
| SMACOffline Algorithm=SMAC, Fine-tuning algorithm=AWR2026.02 | 122.8 | |
| IQLFine-tuning algorithm=TD3+BC, Offline Algorithm=IQL2026.02 | 127 | |
| IQLOffline Algorithm=IQL, Fine-tuning algorithm=AWR2026.02 | 127.9 | |
| TD3+BCOffline Algorithm=TD3+BC, Fine-tuning algorithm=SAC2026.02 | 129.7 | |
| CalQL/CQLOffline Algorithm=CalQL/CQL, Fine-tuning algorithm=AWR2026.02 | 129.9 | |
| CalQL/CQLOffline Algorithm=CalQL/CQL, Fine-tuning algorithm=SAC2026.02 | 134.5 | |
| TD3+BCOffline Algorithm=TD3+BC, Fine-tuning algorithm=AWR2026.02 | 136 | |
| TD3+BCFine-tuning algorithm=TD3+BC, Offline Algorithm=TD3+BC2026.02 | 140.3 | |
| CalQL/CQLFine-tuning algorithm=TD3+BC, Offline Algorithm=CalQL/CQL2026.02 | 140.8 |