Xin Wang, Thomas G. Dietterich. Model-based Policy Gradient Reinforcement Learning. In Tom Fawcett, Nina Mishra, editors, Machine Learning, Proceedings of the Twentieth International Conference (ICML 2003), August 21-24, 2003, Washington, DC, USA. pages 776-783, AAAI Press, 2003.
@inproceedings{WangD03:7, title = {Model-based Policy Gradient Reinforcement Learning}, author = {Xin Wang and Thomas G. Dietterich}, year = {2003}, tags = {rule-based}, researchr = {https://researchr.org/publication/WangD03%3A7}, cites = {0}, citedby = {0}, pages = {776-783}, booktitle = {Machine Learning, Proceedings of the Twentieth International Conference (ICML 2003), August 21-24, 2003, Washington, DC, USA}, editor = {Tom Fawcett and Nina Mishra}, publisher = {AAAI Press}, isbn = {1-57735-189-4}, }