@INPROCEEDINGS{COG8848037,
author={D. J. N. J. {Soemers} and É. {Piette} and M. {Stephenson} and C. {Browne}},
booktitle={2019 IEEE Conference on Games (CoG)},
title={Learning Policies from Self-Play with Policy Gradients and MCTS Value Estimates},
year={2019},
volume={},
number={},
pages={1-8},
keywords={entropy;game theory;learning (artificial intelligence);Monte Carlo methods;tree searching;policy gradient expression;MCTS value estimates;policy gradients;game-playing agents;Monte Carlo tree search algorithms;cross-entropy loss;Games;Linear programming;Standards;Training;Monte Carlo methods;Reinforcement learning;Feature extraction;reinforcement learning;search;self-play},
doi={10.1109/CIG.2019.8848037},
ISSN={2325-4270},
month={Aug},}