Risk-sensitive control has received considerable interest since the seminal work of Howard
and Matheson (Howard and Matheson, 1971/72) because of its ability to account for …

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

In environments with uncertain dynamics exploration is necessary to learn how to perform
well. Existing reinforcement learning algorithms provide strong exploration guarantees, but …

We study risk-sensitive reinforcement learning (RL) based on the entropic risk measure.
Although existing works have established non-asymptotic regret guarantees for this …

We present a reformulation of the stochastic optimal control problem in terms of KL
divergence minimisation, not only providing a unifying perspective of previous approaches …

History is replete with cases wiiere people have worked hard as individuals and groups for
causes they regarded as important; these efforts have ranged in intensity from simple …

We study function approximation for episodic reinforcement learning with entropic risk
measure. We first propose an algorithm with linear function approximation. Compared to …

Markov Decision Processes (MDPs) model problems of sequential decision-making under
uncertainty. They have been studied and applied extensively. Nonetheless, there are two …

We study risk-sensitive reinforcement learning in episodic Markov decision processes with
unknown transition kernels, where the goal is to optimize the total reward under the risk …

The optimized certainty equivalent (OCE) is a family of risk measures that cover important
examples such as entropic risk, conditional value-at-risk and mean-variance models. In this …