Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems

Published in IEEE Trans. Automatic Control (submitted), 2018

Recommended citation: A. Koppel*, E. Tolstaya*, E. Stump, and A. Ribeiro, ”Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems,”, IEEE Trans. Automatic Control (submitted), Mar. 2018. http://katetolstaya.github.io/files/2018_koppel_etal_a.pdf