Policy gradient methods have become a standard for training reinforcement learning agents
in a scalable and efficient manner. However, they do not account for transition uncertainty …

Abstract Robust Markov decision processes (MDPs) aim to handle changing or partially
known system dynamics. To solve them, one typically resorts to robust optimization methods …

Offline reinforcement learning (RL) presents a promising approach for learning reinforced
policies from offline datasets without the need for costly or unsafe interactions with the …

Robust Markov decision processes (MDPs) are used for applications of dynamic
optimization in uncertain environments and have been studied extensively. Many of the …

We build on the optimization-centric view on Bayesian inference advocated by Knoblauch et
al.(2019). Thinking about Bayesian and generalized Bayesian posteriors as the solutions to …

In robust Markov decision processes (RMDPs), it is assumed that the reward and the
transition dynamics lie in a given uncertainty set. By targeting maximal return under the most …

We study robust Markov games (RMG) with $ s $-rectangular uncertainty. We show a
general equivalence between computing a robust Nash equilibrium (RNE) of a $ s …

Mirror descent value iteration (MDVI), an abstraction of Kullback-Leibler (KL) and entropy-
regularized reinforcement learning (RL), has served as the basis for recent high-performing …

We extend temporal-difference (TD) learning in order to obtain risk-sensitive, model-free
reinforcement learning algorithms. This extension can be regarded as modification of the …

Reinforcement learning (RL) is recognized as lacking generalization and robustness under
environmental perturbations, which excessively restricts its application for real-world …