We seek to understand what facilitates sample-efficient learning from historical datasets for
sequential decision-making, a problem that is popularly known as offline reinforcement …

We study data corruption robustness for reinforcement learning with human feedback
(RLHF) in an offline setting. Given an offline dataset of pairs of trajectories along with …

Offline reinforcement learning (RL) aims to learn a policy that maximizes the expected
cumulative reward using a pre-collected dataset. Offline RL with low-rank MDPs or general …

In this paper, we study the offline RL problem with linear function approximation. Our main
structural assumption is that the MDP has low inherent Bellman error, which stipulates that …

We study offline Reinforcement Learning in large infinite-horizon discounted Markov
Decision Processes (MDPs) when the reward and transition models are linearly realizable …

We study offline reinforcement learning (RL) with linear MDPs under the infinite-horizon
discounted setting which aims to learn a policy that maximizes the expected discounted …

Inspired by the recent successes of Inverse Optimization (IO) across various application
domains, we propose a novel offline Reinforcement Learning (ORL) algorithm for …

Reinforcement Learning (RL) is an area of machine learning where an intelligent agent
solves sequential decision-making problems based on experience. Recent advances in the …