While policy-based reinforcement learning (RL) achieves tremendous successes in practice,
it is significantly less understood in theory, especially compared with value-based RL. In …

Reinforcement learning is a learning paradigm concerned with learning to control a system
so as to maximize a numerical performance measure that expresses a long-term objective …

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 propose a general framework for entropy-regularized average-reward reinforcement
learning in Markov decision processes (MDPs). Our approach is based on extending the …

We investigate the problem of corruption robustness in offline reinforcement learning (RL)
with general function approximation, where an adversary can corrupt each sample in the …

We consider the task of learning in episodic finite-horizon Markov decision processes with
an unknown transition function, bandit feedback, and adversarial losses. We propose an …

We consider online learning in episodic loop-free Markov decision processes (MDPs),
where the loss function can change arbitrarily between episodes, and the transition function …

Despite the significant interest and progress in reinforcement learning (RL) problems with
adversarial corruption, current works are either confined to the linear setting or lead to an …

We study the {\em combinatorial pure exploration (CPE)} problem in the stochastic multi-
armed bandit setting, where a learner explores a set of arms with the objective of identifying …

We develop a model selection approach to tackle reinforcement learning with adversarial
corruption in both transition and reward. For finite-horizon tabular MDPs, without prior …