This paper studies tabular reinforcement learning (RL) in the hybrid setting, which assumes
access to both an offline dataset and online interactions with the unknown environment. A …

We investigate a novel safe reinforcement learning problem with step-wise violation
constraints. Our problem differs from existing works in that we focus on stricter step-wise …

This paper studies reward-agnostic exploration in reinforcement learning (RL)—a scenario
where the learner is unware of the reward functions during the exploration stage—and …

Safety is a crucial necessity in many applications of reinforcement learning (RL), whether
robotic, automotive, or medical. Many existing approaches to safe RL rely on receiving …

This paper investigates conservative exploration in reinforcement learning where the
performance of the learning agent is guaranteed to be above a certain threshold throughout …

We study how to report few-shot imitation (FSI) policies' behavior errors in novel
environments, a novel task named adaptable error detection (AED). The potential to cause …