ResearchBenchmarksOffline-to-online Reinforcement Learning on D4RL KitchenOffline-to-online Reinforcement Learning on D4RL KitchenFollow131.4RegretSMAC106.156276.553446.95617.347Feb 19, 2026Evaluation resultsMethodMethodLinksRegretSMACOffline Algorithm=SMAC...Offline Algorithm=SMAC, Fine-tuning algorithm=SAC2026.02131.4CalQL/CQLOffline Algorithm=CalQ...Offline Algorithm=CalQL/CQL, Fine-tuning algorithm=SAC2026.02467.1IQLOffline Algorithm=IQL,...Offline Algorithm=IQL, Fine-tuning algorithm=SAC2026.02492.9TD3+BCOffline Algorithm=TD3+...Offline Algorithm=TD3+BC, Fine-tuning algorithm=SAC2026.02762.5