@article{unifyingvalueiterationadvantagelearning, title = {Unifying Value Iteration, Advantage Learning, and Dynamic Policy Programming}, author = {Tadashi Kozuno and Eiji Uchibe and Kenji Doya}, year = {2017}, eprint = {1710.10866}, archivePrefix = {arXiv}, url = {http://arxiv.org/abs/1710.10866v1}, }