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

Ekaterina V. Tolstaya, Alec Koppel, Ethan Stump, Alejandro Ribeiro. Nonparametric Stochastic Compositional Gradient Descent for Q-Learning in Continuous Markov Decision Problems. In 2018 Annual American Control Conference, ACC 2018, Milwaukee, WI, USA, June 27-29, 2018. pages 6608-6615, IEEE, 2018. [doi]

Authors

Ekaterina V. Tolstaya

This author has not been identified. Look up 'Ekaterina V. Tolstaya' in Google

Alec Koppel

This author has not been identified. Look up 'Alec Koppel' in Google

Ethan Stump

This author has not been identified. Look up 'Ethan Stump' in Google

Alejandro Ribeiro

This author has not been identified. Look up 'Alejandro Ribeiro' in Google