Andrey Bernstein, Yue Chen, Marcello Colombino, Emiliano Dall'Anese, Prashant G. Mehta, Sean Meyn. Quasi-Stochastic Approximation and Off-Policy Reinforcement Learning. In 58th IEEE Conference on Decision and Control, CDC 2019, Nice, France, December 11-13, 2019. pages 5244-5251, IEEE, 2019. [doi]
Abstract is missing.