PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Experts in a Markov Decision Process
Eyal Even-Dar, Sham Kakade and Yishay Mansour
In: NIPS, December 14-16, 2004, Vancouver, B.C., Canada.

This is the latest version of this eprint.


We consider the MDP setting in which the reward function is chosen arbitrarily (possibly by an adversary) during each time step of play, yet the dynamics remain fixed. Similar to the experts setting, we address the question of how well can an agent do when compared to the reward achieved under the best stationary policy over time. We provide \emph{efficient} algorithms, which have regret bounds with \emph{no dependence} on the size of state space. Instead, these bounds depend only on a certain horizon time of the process and logarithmically on the number of actions. We also show that in the case that the dynamics change over time, the problem becomes computationally hard.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Theory & Algorithms
ID Code:477
Deposited By:Yishay Mansour
Deposited On:23 December 2004

Available Versions of this Item