Most reinforcement learning methods are based upon the key assumption that the transition
dynamics and reward functions are fixed, that is, the underlying Markov decision process is …

We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs)
with linear function approximation under drifting environment. Specifically, both the reward …

Cascading bandits is a natural and popular model that frames the task of learning to rank
from Bernoulli click feedback in a bandit setting. For the case of unstructured rewards, we …

Methods for sequential decision-making are often built upon a foundational assumption that
the underlying decision process is stationary. This limits the application of such methods …

In this paper, we investigate the non-stationary combinatorial semi-bandit problem, both in
the switching case and in the dynamic case. In the general case where (a) the reward …

THIS PAPER IS ELIGIBLE FOR THE STUDENT PAPER AWARD. A finite horizon variant of
the quickest change detection problem is studied, in which the goal is to minimize a delay …

This paper studies the adversarial graphical contextual bandits, a variant of adversarial multi-
armed bandits that leverage two categories of the most common side information: contexts …

We study a structured multi-agent multi-armed bandit (MAMAB) problem in a dynamic
environment. A graph reflects the information-sharing structure among agents, and the arms' …

A finite-horizon variant of the quickest change detection problem is investigated, which is
motivated by a change detection problem that arises in piecewise stationary bandits. The …

A finite horizon variant of the quickest change detection problem is studied, in which the goal
is to minimize a delay threshold (latency), under constraints on the probability of false alarm …