Reinforcement learning (RL) techniques optimize the accumulated long-term reward of a
suitably chosen reward function. However, designing such a reward function often requires …

In practice, preference learning from human feedback depends on incomplete data with
hidden context. Hidden context refers to data that affects the feedback received, but which is …

This paper explores the preference-based top-K rank aggregation problem. Suppose that a
collection of items is repeatedly compared in pairs, and one wishes to recover a consistent …

In machine learning, the notion of multi-armed bandits refers to a class of online learning
problems, in which an agent is supposed to simultaneously explore and exploit a given set …

Learning from human feedback has shown to be a useful approach in acquiring robot
reward functions. However, expert feedback is often assumed to be drawn from an …

We study the $ K $-armed contextual dueling bandit problem, a sequential decision making
setting in which the learner uses contextual information to make two decisions, but only …

We consider the problem of learning to choose actions using contextual information when
provided with limited feedback in the form of relative pairwise comparisons. We study this …

A version of the dueling bandit problem is addressed in which a Condorcet winner may not
exist. Two algorithms are proposed that instead seek to minimize regret with respect to the …

We study the problem of online rank elicitation, assuming that rankings of a set of
alternatives obey the Plackett-Luce distribution. Following the setting of the dueling bandits …

The dueling bandits problem is an online learning framework where learning happens “on-
thefly” through preference feedback, ie, from comparisons between a pair of actions. Unlike …