Roi Ceren, Prashant Doshi, Bikramjit Banerjee. Reinforcement Learning in Partially Observable Multiagent Settings: Monte Carlo Exploring Policies with PAC Bounds. In Catholijn M. Jonker, Stacy Marsella, John Thangarajah, Karl Tuyls, editors, Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems, Singapore, May 9-13, 2016. pages 530-538, ACM, 2016. [doi]
@inproceedings{CerenDB16, title = {Reinforcement Learning in Partially Observable Multiagent Settings: Monte Carlo Exploring Policies with PAC Bounds}, author = {Roi Ceren and Prashant Doshi and Bikramjit Banerjee}, year = {2016}, url = {http://dl.acm.org/citation.cfm?id=2937002}, researchr = {https://researchr.org/publication/CerenDB16}, cites = {0}, citedby = {0}, pages = {530-538}, booktitle = {Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems, Singapore, May 9-13, 2016}, editor = {Catholijn M. Jonker and Stacy Marsella and John Thangarajah and Karl Tuyls}, publisher = {ACM}, isbn = {978-1-4503-4239-1}, }