We study matrix estimation problems arising in reinforcement learning with low-rank
structure. In low-rank bandits, the matrix to be recovered specifies the expected arm …

We consider the problem of latent bandits with cluster structure where there are multiple
users, each with an associated multi-armed bandit problem. These users are grouped into …

We investigate the low rank matrix completion problem in an online setting with ${M} $
users, ${N} $ items, ${T} $ rounds, and an unknown rank-$ r $ reward matrix ${R}\in\mathbb …

We consider the problem of\emph {blocked} collaborative bandits where there are multiple
users, each with an associated multi-armed bandit problem. These users are grouped …

We consider collaborative multi-user reinforcement learning, where multiple users have the
same state-action space and transition probabilities but different rewards. Under the …

In many digital contexts such as online news and e-tailing with many new users and items,
recommendation systems face several challenges: i) how to make initial recommendations …

In this work, we consider the problem of collaborative multi-user reinforcement learning. In
this setting there are multiple users with the same state-action space and transition …

Maternal mortality is unacceptably high in several parts of the world. In 2020, an estimated
287,000 women died from preventable causes related to pregnancy and childbirth [30] …

Online matching markets face increasing needs to accurately learn the matching qualities
between demand and supply for effective design of matching policies. However, the growing …

This dissertation investigates online algorithms and beyond worst-case learning, focusing
on an array of problems that showcase the applicability of online algorithms to derive robust …