Rewards Structure in Games: Learning a Compact Representation for Action Space.

Margot Lisa-Jing Yann Yves Lespérance Aijun An

Published in: AAAI Workshops (2017)

Keyphrases

reinforcement learning
markov decision processes
learning algorithm
prior knowledge
state space
search algorithm
pairwise
action space
machine learning
cooperative
computational complexity
hidden markov models
supervised learning
hidden variables