In this article, we aim to provide a literature review of different formulations and approaches
to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We …

We propose a black-box reduction that turns a certain reinforcement learning algorithm with
optimal regret in a (near-) stationary environment into another algorithm with optimal …

We initiate the study of episodic reinforcement learning under adversarial corruptions in both
the rewards and the transition probabilities of the underlying system extending recent results …

We consider model-free reinforcement learning (RL) in non-stationary Markov decision
processes. Both the reward functions and the state transition functions are allowed to vary …

We consider primal-dual-based reinforcement learning (RL) in episodic constrained Markov
decision processes (CMDPs) with non-stationary objectives and constraints, which plays a …

Abstract We investigate online Markov Decision Processes (MDPs) with adversarially
changing loss functions and known transitions. We choose dynamic regret as the …

We study model-free reinforcement learning (RL) algorithms in episodic non-stationary
constrained Markov decision processes (CMDPs), in which an agent aims to maximize the …

General function approximation is a powerful tool to handle large state and action spaces in
a broad range of reinforcement learning (RL) scenarios. However, theoretical understanding …

We introduce the framework of performative reinforcement learning where the policy chosen
by the learner affects the underlying reward and transition dynamics of the environment …

We study episodic reinforcement learning in non-stationary linear (aka low-rank) Markov
Decision Processes (MDPs), ie, both the reward and transition kernel are linear with respect …