Statistics Papers
Document Type
Conference Paper
Date of this Version
2004
Publication Source
Advances in Neural Information Processing Systems
Volume
17
Abstract
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.
Recommended Citation
Even-Dar, E., Kakade, S., & Mansour, Y. (2004). Experts in a Markov Decision Process. Advances in Neural Information Processing Systems, 17 Retrieved from https://repository.upenn.edu/statistics_papers/457
Date Posted: 27 November 2017