André Barreto, Shaobo Hou, Diana Borsa, David Silver, Doina Precup. Fast reinforcement learning with generalized policy updates. Proc. Natl. Acad. Sci. USA, 117(48):30079-30087, 2020. [doi]
@article{BarretoHBSP20, title = {Fast reinforcement learning with generalized policy updates}, author = {André Barreto and Shaobo Hou and Diana Borsa and David Silver and Doina Precup}, year = {2020}, doi = {10.1073/pnas.1907370117}, url = {https://doi.org/10.1073/pnas.1907370117}, researchr = {https://researchr.org/publication/BarretoHBSP20}, cites = {0}, citedby = {0}, journal = {Proc. Natl. Acad. Sci. USA}, volume = {117}, number = {48}, pages = {30079-30087}, }