Timezone: »

Confidence-Budget Matching for Sequential Budgeted Learning
Yonathan Efroni · Nadav Merlis · Aadirupa Saha · Shie Mannor

Wed Jul 21 05:25 PM -- 05:30 PM (PDT) @ None

A core element in decision-making under uncertainty is the feedback on the quality of the performed actions. However, in many applications, such feedback is restricted. For example, in recommendation systems, repeatedly asking the user to provide feedback on the quality of recommendations will annoy them. In this work, we formalize decision-making problems with querying budget, where there is a (possibly time-dependent) hard limit on the number of reward queries allowed. Specifically, we focus on multi-armed bandits, linear contextual bandits, and reinforcement learning problems. We start by analyzing the performance of `greedy' algorithms that query a reward whenever they can. We show that in fully stochastic settings, doing so performs surprisingly well, but in the presence of any adversity, this might lead to linear regret. To overcome this issue, we propose the Confidence-Budget Matching (CBM) principle that queries rewards when the confidence intervals are wider than the inverse square root of the available budget. We analyze the performance of CBM based algorithms in different settings and show that it performs well in the presence of adversity in the contexts, initial states, and budgets.

Author Information

Yonathan Efroni (Microsoft Research, New York)
Nadav Merlis (Technion)
Aadirupa Saha (Microsoft Research)
Shie Mannor (Technion)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors