Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition

Part of Proceedings of the International Conference on Machine Learning 1 pre-proceedings (ICML 2020)

Bibtex »Metadata »Paper »Supplemental »

Bibtek download is not availble in the pre-proceeding


Chi Jin, Tiancheng Jin, Haipeng Luo, Suvrit Sra, Tiancheng Yu


<p>We consider the task of learning in episodic finite-horizon Markov decision processes with an unknown transition function, bandit feedback, and adversarial losses. We propose an efficient algorithm that achieves O(√L|X|AT ) regret with high probability, where L is the horizon, |X| the number of states, |A| the number of actions, and T the number of episodes. To our knowledge, our algorithm is the first to ensure O(√T) regret in this challenging setting; in fact, it achieves the same regret as (Rosenberg &amp; Mansour, 2019a) who consider the easier setting with full-information. Our key contributions are two-fold: a tighter confidence set for the transition function; and an optimistic loss estimator that is inversely weighted by an "upper occupancy bound". </p>