%0 Journal Article %1 journals/corr/abs-1912-02714 %A Trabucco, Brandon %A Qu, Albert %A Li, Simon %A Ashokavardhanan, Ganeshkumar %D 2019 %J CoRR %K dblp %T Inferring the Optimal Policy using Markov Chain Monte Carlo. %U http://dblp.uni-trier.de/db/journals/corr/corr1912.html#abs-1912-02714 %V abs/1912.02714

@article{journals/corr/abs-1912-02714, added-at = {2020-01-02T00:00:00.000+0100}, author = {Trabucco, Brandon and Qu, Albert and Li, Simon and Ashokavardhanan, Ganeshkumar}, biburl = {https://www.bibsonomy.org/bibtex/2db757c6ea31c903671e9be532767f325/dblp}, ee = {http://arxiv.org/abs/1912.02714}, interhash = {9c77b0ea78ea58a52328e5420bdbb680}, intrahash = {db757c6ea31c903671e9be532767f325}, journal = {CoRR}, keywords = {dblp}, timestamp = {2020-01-03T11:39:53.000+0100}, title = {Inferring the Optimal Policy using Markov Chain Monte Carlo.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr1912.html#abs-1912-02714}, volume = {abs/1912.02714}, year = 2019 }