papers AI Learner
The Github is limit! Click to go to the new site.

Online Convex Optimization in Adversarial Markov Decision Processes

2019-05-19
Aviv Rosenberg, Yishay Mansour

Abstract

We consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes, and the transition function is not known to the learner. We show $\tilde{O}(L|X|\sqrt{|A|T})$ regret bound, where $T$ is the number of episodes, $X$ is the state space, $A$ is the action space, and $L$ is the length of each episode. Our online algorithm is implemented using entropic regularization methodology, which allows to extend the original adversarial MDP model to handle convex performance criteria (different ways to aggregate the losses of a single episode) , as well as improve previous regret bounds.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.07773

PDF

http://arxiv.org/pdf/1905.07773


Similar Posts

Comments