Decision-making in the face of uncertainty is a significant challenge in machine learning,
and the multi-armed bandit model is a commonly used framework to address it. This …

In many sequential decision-making problems, the goal is to optimize a utility function while
satisfying a set of constraints on different utilities. This learning problem is formalized …

We address the issue of safety in reinforcement learning. We pose the problem in an
episodic framework of a constrained Markov decision process. Existing results have shown …

The contextual bandit literature has traditionally focused on algorithms that address the
exploration–exploitation tradeoff. In particular, greedy algorithms that exploit current …

Bandit algorithms have various application in safety-critical systems, where it is important to
respect the system constraints that rely on the bandit's unknown parameters at every round …

We study a constrained contextual linear bandit setting, where the goal of the agent is to
produce a sequence of policies, whose expected cumulative reward over the course of …

In performative prediction, the deployment of a predictive model triggers a shift in the data
distribution. As these shifts are typically unknown ahead of time, the learner needs to deploy …

We study a stochastic bandit problem with a general unknown reward function and a
general unknown constraint function. Both functions can be non-linear (even non-convex) …

This paper considers stochastic linear bandits with general nonlinear constraints. The
objective is to maximize the expected cumulative reward over horizon $ T $ subject to a set …

We present RobinHood, an offline contextual bandit algorithm designed to satisfy a broad
family of fairness constraints. Our algorithm accepts multiple fairness definitions and allows …