Yohei Takamori, Yuko Osana. Profit sharing that can learn deterministic policy for POMDPs environments. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Anchorage, Alaska, USA, October 9-12, 2011. pages 490-495, IEEE, 2011. [doi]
@inproceedings{TakamoriO11, title = {Profit sharing that can learn deterministic policy for POMDPs environments}, author = {Yohei Takamori and Yuko Osana}, year = {2011}, doi = {10.1109/ICSMC.2011.6083713}, url = {http://dx.doi.org/10.1109/ICSMC.2011.6083713}, researchr = {https://researchr.org/publication/TakamoriO11}, cites = {0}, citedby = {0}, pages = {490-495}, booktitle = {Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Anchorage, Alaska, USA, October 9-12, 2011}, publisher = {IEEE}, isbn = {978-1-4577-0652-3}, }