Settling the sample complexity of model-based offline reinforcement learning Page 1 The
Annals of Statistics 2024, Vol. 52, No. 1, 233–260 https://doi.org/10.1214/23-AOS2342 © …

This paper concerns the central issues of model robustness and sample efficiency in offline
reinforcement learning (RL), which aims to learn to perform decision making from history …

We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source
domain and deployed to a distinct target domain. We aim to solve this problem via online …

Robustness has been extensively studied in reinforcement learning (RL) to handle various
forms of uncertainty such as random perturbations, rare events, and malicious attacks. In this …

Distributionally robust offline reinforcement learning (RL), which seeks robust policy training
against environment perturbation by modeling dynamics uncertainty, calls for function …

A central issue lying at the heart of online reinforcement learning (RL) is data efficiency.
While a number of recent works achieved asymptotically minimal regret in online RL, the …

To overcome the sim-to-real gap in reinforcement learning (RL), learned policies must
maintain robustness against environmental uncertainties. While robust RL has been widely …

In offline reinforcement learning (RL), the absence of active exploration calls for attention on
the model robustness to tackle the sim-to-real gap, where the discrepancy between the …

Three major challenges in reinforcement learning are the complex dynamical systems with
large state spaces, the costly data acquisition processes, and the deviation of real-world …

We study the sample complexity of obtaining an $\epsilon $-optimal policy in\emph {Robust}
discounted Markov Decision Processes (RMDPs), given only access to a generative model …