5 papers · 1 filter
Preference-centric Bandits: Optimality of Mixtures and Regret-efficient Algorithms
Meltem Tatlı, Arpan Mukherjee, Prashanth L. A. +2
The objective of canonical multi-armed bandits is to identify and repeatedly select an arm with the largest reward, often in the form of the expected value of the arm's probability…
Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms
Meltem Tatlı, Arpan Mukherjee, Prashanth L. A. +2
This paper introduces a general framework for risk-sensitive bandits that integrates the notions of risk-sensitive objectives by adopting a rich class of distortion riskmetrics. Th…
Linear Causal Bandits: Unknown Graph and Soft Interventions
Zirui Yan, Ali Tajer
Designing causal bandit algorithms depends on two central categories of assumptions: (i) the extent of information about the underlying causal graphs and (ii) the extent of informa…
Optimal Best Arm Identification with Fixed Confidence in Restless Bandits
P. N. Karthik, Vincent Y. F. Tan, Arpan Mukherjee +1
We study best arm identification in a restless multi-armed bandit setting with finitely many arms. The discrete-time data generated by each arm forms a homogeneous Markov chain tak…
Improved Bound for Robust Causal Bandits with Linear Models
Zirui Yan, Arpan Mukherjee, Burak Varıcı +1
This paper investigates the robustness of causal bandits (CBs) in the face of temporal model fluctuations. This setting deviates from the existing literature's widely-adopted assum…