The success of reinforcement learning in a variety of challenging sequential decision-
making problems has been much discussed, but often ignored in this discussion is the …

We study bandit model selection in stochastic environments. Our approach relies on a
master algorithm that selects between candidate base algorithms. We develop a master …

POMDPs capture a broad class of decision making problems, but hardness results suggest
that learning is intractable even in simple settings due to the inherent partial observability …

We develop a model selection approach to tackle reinforcement learning with adversarial
corruption in both transition and reward. For finite-horizon tabular MDPs, without prior …

Best-of-both-worlds algorithms for online learning which achieve near-optimal regret in both
the adversarial and the stochastic regimes have received growing attention recently …

We study the problem of representational transfer in RL, where an agent first pretrains in a
number of\emph {source tasks} to discover a shared representation, which is subsequently …

Reward design is one of the most critical and challenging aspects when formulating a task
as a reinforcement learning (RL) problem. In practice, it often takes several attempts of …

We study the problem of model selection in bandit scenarios in the presence of nested
policy classes, with the goal of obtaining simultaneous adversarial and stochastic (``best of …

We study the problem of experiment planning with function approximation in contextual
bandit problems. In settings where there is a significant overhead to deploying adaptive …

Multi-agent reinforcement learning (MARL) problems are challenging due to information
asymmetry. To overcome this challenge, existing methods often require high level of …