We present a novel Q-learning algorithm tailored to solve distributionally robust Markov
decision problems where the corresponding ambiguity set of transition probabilities for the …

In this paper we develop a Stochastic Gradient Langevin Dynamics (SGLD) algorithm
tailored for solving a certain class of non-convex distributionally robust optimisation …

Robust Markov Decision Processes (RMDPs) are a widely used framework for sequential
decision-making under parameter uncertainty. RMDPs have been extensively studied when …

We develop a generic policy gradient method with the global optimality guarantee for robust
Markov Decision Processes (MDPs). While policy gradient methods are widely used for …

Robust reinforcement learning is essential for deploying reinforcement learning algorithms
in real-world scenarios where environmental uncertainty predominates. Traditional robust …

Many classic Reinforcement Learning (RL) algorithms rely on a Bellman operator, which
involves an expectation over the next states, leading to the concept of bootstrapping. To …

In this note we provide an upper bound for the difference between the value function of a
distributionally robust Markov decision problem and the value function of a non-robust …

Robust Markov decision process (robust MDP) is an important machine learning framework
to make a reliable policy that is robust to environmental perturbation. Despite empirical …

Robust Markov Decision Processes (MDPs) and risk-sensitive MDPs are both powerful tools
for making decisions in the presence of uncertainties. Previous efforts have aimed to …

Reinforcement Learning (RL) problem with general utility is a powerful decision making
framework that covers standard RL with cumulative cost, exploration problems, and …