%0 Journal Article %1 journals/corr/abs-2205-15891 %A Cisneros-Velarde, Pedro %A Lyu, Boxiang %A Koyejo, Sanmi %A Kolar, Mladen %D 2022 %J CoRR %K dblp %T One Policy is Enough: Parallel Exploration with a Single Policy is Minimax Optimal for Reward-Free Reinforcement Learning. %U http://dblp.uni-trier.de/db/journals/corr/corr2205.html#abs-2205-15891 %V abs/2205.15891

@article{journals/corr/abs-2205-15891, added-at = {2022-06-01T00:00:00.000+0200}, author = {Cisneros-Velarde, Pedro and Lyu, Boxiang and Koyejo, Sanmi and Kolar, Mladen}, biburl = {https://www.bibsonomy.org/bibtex/2641878e28e82d141124a05641b9aed21/dblp}, ee = {https://doi.org/10.48550/arXiv.2205.15891}, interhash = {467372ae54b16699a7b1c843efdf083e}, intrahash = {641878e28e82d141124a05641b9aed21}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T23:59:08.000+0200}, title = {One Policy is Enough: Parallel Exploration with a Single Policy is Minimax Optimal for Reward-Free Reinforcement Learning.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2205.html#abs-2205-15891}, volume = {abs/2205.15891}, year = 2022 }