We study the problem of estimating the distribution of the return of a policy using an offline
dataset that is not generated from the policy, ie, distributional offline policy evaluation (OPE) …

While distributional reinforcement learning (DistRL) has been empirically effective, the
question of when and why it is better than vanilla, non-distributional RL has remained …

In this paper, we prove that Distributional Reinforcement Learning (DistRL), which learns the
return distribution, can obtain second-order bounds in both online and offline RL in general …

Reinforcement learning (RL) allows an agent interacting sequentially with an environment to
maximize its long-term expected return. In the distributional RL (DistrRL) paradigm, the …

In the realm of reinforcement learning (RL), accounting for risk is crucial for making
decisions under uncertainty, particularly in applications where safety and reliability are …

Quantifying uncertainty about a policy's long-term performance is important to solve
sequential decision-making tasks. We study the problem from a model-based Bayesian …

Although distributional reinforcement learning (DRL) has been widely examined in the past
few years, very few studies investigate the validity of the obtained Q-function estimator in the …

Feature preprocessing continues to play a critical role when applying machine learning and
statistical methods to tabular data. In this paper, we propose the use of the kernel density …

Abstract The Maximum Entropy (Max-Ent) framework has been effectively employed in a
variety of Reinforcement Learning (RL) tasks. In this paper, we first propose a novel Max-Ent …

Distributional reinforcement learning (DRL) enhances the understanding of the effects of the
randomness in the environment by letting agents learn the distribution of a random return …