Offline-to-online Reinforcement Learning on walker2d
544.4RegretSMAC
Evaluation results
| Method | Links | |
|---|---|---|
| SMACOffline Algorithm=SMAC, Fine-tuning algorithm=AWR2026.02 | 544.4 | |
| CalQL/CQLOffline Algorithm=CalQL/CQL, Fine-tuning algorithm=AWR2026.02 | 1,136.9 | |
| SMACFine-tuning algorithm=TD3+BC, Offline Algorithm=SMAC2026.02 | 1,232.3 | |
| TD3+BCFine-tuning algorithm=TD3+BC, Offline Algorithm=TD3+BC2026.02 | 1,242.6 | |
| IQLFine-tuning algorithm=TD3+BC, Offline Algorithm=IQL2026.02 | 1,548.6 | |
| IQLOffline Algorithm=IQL, Fine-tuning algorithm=AWR2026.02 | 1,918.7 | |
| TD3+BCOffline Algorithm=TD3+BC, Fine-tuning algorithm=AWR2026.02 | 1,988.4 | |
| CalQL/CQLFine-tuning algorithm=TD3+BC, Offline Algorithm=CalQL/CQL2026.02 | 2,642.5 |