< BK21 플러스 BEST 정보기술 사업단 세미나 개최 안내 >

개최일시 : 2015년 12월 22일 화요일 11:00 ~ 12:00

개최장소 : 제 2공학관 B701호

세미나 제목 : On the Whittle Index for Restless Multi-armed Hidden Markov Bandits

발표초록 :

We consider a restless multi-armed bandit in which each arm can be in one two states. When an arm is sampled, the state of the arm is not available to the sampler. Instead, a binary signal with a known randomness that depends on the state of the arm is made available. No signal is displayed if the arm is not sampled. An arm-dependent reward is accrued from each sampling. In each time step, each arm changes state according to known transition probabilities which in turn depend on whether the arm is sampled or not sampled. Since the state of the arm is never visible and has to be inferred from the current belief and a possible binary signal, we call this the hidden Markov bandit. Our interest is in a policy to select the arm(s) in each time step that maximises the infinite horizon discounted reward. Specifically, we seek the use of Whittle’s index in selecting the arms.

We first analyze the single-armed bandit and show that it admits an approximate threshold-type optimal policy when the ‘no-sample’ action is subsidised. Next, we show that this also satisfies an approximate- indexability property. Numerical examples support the analytical results.

강연자 : D. Manjunath / IIT Bombay, India

초청자 : 전기전자공학과 교수 이장원