Piecewise-stationary bandit problems with side observations

We consider a sequential decision problem where the rewards are generated by a piecewise-stationary distribution. However, the different reward distributions are unknown and may change at unknown instants. Our approach uses a limited number of side observations on past rewards, but does not require prior knowledge of the frequency of changes. In spite of the adversarial nature of the reward process, we provide an algorithm whose regret, with respect to the baseline with perfect knowledge of the distributions and the changes, is O(k log(T )), where k is the number of changes up to time T . This is in contrast to the case where side observations are not available, and where the regret is at least ( T).

• Type: Conference
• Year: 2009
• Where: ICML
• Authors: Jia Yuan Yu, Shie Mannor
• Keywords: ICML 2009, Machine Learning, Past Rewards, Reward Process, Sequential Decision Problem