Average reward reinforcement learning with unknown mixing times.
Tom Zahavy, Alon Cohen, Haim Y. Kaplan, Yishay Mansour · arXiv (Cornell University) · 2019
We derive and analyze learning algorithms for apprenticeship learning, policy evaluation, and policy gradient for average reward criteria. Existing algorithms explicitly require an upper bound on the mixing time. In contrast, we build on ideas from Markov chain theory and derive sampling algorithms that do not require such an upper bound. For these algorithms, we provide theoretical bounds on their sample-complexity and running time.