%0 Journal Article %1 journals/corr/abs-2106-11854 %A Han, Beining %A Ren, Zhizhou %A Wu, Zuofan %A Zhou, Yuan %A Peng, Jian %D 2021 %J CoRR %K dblp %T Off-Policy Reinforcement Learning with Delayed Rewards. %U http://dblp.uni-trier.de/db/journals/corr/corr2106.html#abs-2106-11854 %V abs/2106.11854

@article{journals/corr/abs-2106-11854, added-at = {2021-06-30T00:00:00.000+0200}, author = {Han, Beining and Ren, Zhizhou and Wu, Zuofan and Zhou, Yuan and Peng, Jian}, biburl = {https://www.bibsonomy.org/bibtex/21569dd5de11f8eb16f9f0070e53e9448/dblp}, ee = {https://arxiv.org/abs/2106.11854}, interhash = {649ce2c8970dca5b5839e22aaf126d24}, intrahash = {1569dd5de11f8eb16f9f0070e53e9448}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-09T00:19:00.000+0200}, title = {Off-Policy Reinforcement Learning with Delayed Rewards.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2106.html#abs-2106-11854}, volume = {abs/2106.11854}, year = 2021 }