Experts in a Markov Decision Process

We consider an MDP setting in which the reward function is allowed to change during each time step of play (possibly in an adversarial manner), 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 efficient algorithms, which have regret bounds with 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.

• Type: Conference
• Year: 2004
• Where: NIPS
• Authors: Eyal Even-Dar, Sham M. Kakade, Yishay Mansour
• Keywords: MDP Setting, NIPS 2004, NIPS 2007, Reward Function, Time Step