Seiji Ishihara, Harukazu Igarashi. Policy Gradient Reinforcement Learning with Environmental Dynamics and Action-Values in Policies. In Andreas König, Andreas Dengel, Knut Hinkelmann, Koichi Kise, Robert J. Howlett, Lakhmi C. Jain, editors, Knowledge-Based and Intelligent Information and Engineering Systems - 15th International Conference, KES 2011, Kaiserslautern, Germany, September 12-14, 2011, Proceedings, Part I. Volume 6881 of Lecture Notes in Computer Science, pages 120-130, Springer, 2011. [doi]
@inproceedings{IshiharaI11-0, title = {Policy Gradient Reinforcement Learning with Environmental Dynamics and Action-Values in Policies}, author = {Seiji Ishihara and Harukazu Igarashi}, year = {2011}, doi = {10.1007/978-3-642-23851-2_13}, url = {http://dx.doi.org/10.1007/978-3-642-23851-2_13}, researchr = {https://researchr.org/publication/IshiharaI11-0}, cites = {0}, citedby = {0}, pages = {120-130}, booktitle = {Knowledge-Based and Intelligent Information and Engineering Systems - 15th International Conference, KES 2011, Kaiserslautern, Germany, September 12-14, 2011, Proceedings, Part I}, editor = {Andreas König and Andreas Dengel and Knut Hinkelmann and Koichi Kise and Robert J. Howlett and Lakhmi C. Jain}, volume = {6881}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, isbn = {978-3-642-23850-5}, }