Reinforcement Learning Based Solution to Two-player Zero-sum Game Using Differentiator.

Xinxin Guo Weisheng Yan Peng Cui Shouxu Zhang

Published in: ICARM (2018)

Keyphrases

reinforcement learning
state space
educational games
optimal solution
linear equations
game playing
game theory
game design
closed form
control policy
online game
function approximation
video games
data sets
optimal policy
supervised learning
learning process
machine learning