Tobias Graf, Marco Platzner. Adaptive Playouts in Monte-Carlo Tree Search with Policy-Gradient Reinforcement Learning. In Aske Plaat, H. Jaap van den Herik, Walter A. Kosters, editors, Advances in Computer Games - 14th International Conference, ACG 2015, Leiden, The Netherlands, July 1-3, 2015, Revised Selected Papers. Volume 9525 of Lecture Notes in Computer Science, pages 1-11, Springer, 2015. [doi]
@inproceedings{GrafP15, title = {Adaptive Playouts in Monte-Carlo Tree Search with Policy-Gradient Reinforcement Learning}, author = {Tobias Graf and Marco Platzner}, year = {2015}, doi = {10.1007/978-3-319-27992-3_1}, url = {http://dx.doi.org/10.1007/978-3-319-27992-3_1}, researchr = {https://researchr.org/publication/GrafP15}, cites = {0}, citedby = {0}, pages = {1-11}, booktitle = {Advances in Computer Games - 14th International Conference, ACG 2015, Leiden, The Netherlands, July 1-3, 2015, Revised Selected Papers}, editor = {Aske Plaat and H. Jaap van den Herik and Walter A. Kosters}, volume = {9525}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, isbn = {978-3-319-27991-6}, }