%0 Journal Article %1 journals/corr/abs-2310-08558 %A Mark, Max Sobol %A Sharma, Archit %A Tajwar, Fahim %A Rafailov, Rafael %A Levine, Sergey %A Finn, Chelsea %D 2023 %J CoRR %K dblp %T Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias. %U http://dblp.uni-trier.de/db/journals/corr/corr2310.html#abs-2310-08558 %V abs/2310.08558

@article{journals/corr/abs-2310-08558, added-at = {2023-10-25T00:00:00.000+0200}, author = {Mark, Max Sobol and Sharma, Archit and Tajwar, Fahim and Rafailov, Rafael and Levine, Sergey and Finn, Chelsea}, biburl = {https://www.bibsonomy.org/bibtex/2a4a251d2ab92367863cd99d8c6199efa/dblp}, ee = {https://doi.org/10.48550/arXiv.2310.08558}, interhash = {6da09b57f777b8dc97844805db0df13f}, intrahash = {a4a251d2ab92367863cd99d8c6199efa}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T22:20:56.000+0200}, title = {Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2310.html#abs-2310-08558}, volume = {abs/2310.08558}, year = 2023 }