Deep reinforcement learning (DRL) and deep multiagent reinforcement learning (MARL)
have achieved significant success across a wide range of domains, including game artificial …

We analyse quantile temporal-difference learning (QTD), a distributional reinforcement
learning algorithm that has proven to be a key component in several successful large-scale …

Multi-agent systems are characterized by environmental uncertainty, varying policies of
agents, and partial observability, which result in significant risks. In the context of Multi-Agent …

A major task of sports analytics is player evaluation. Previous methods commonly measured
the impact of players' actions on desirable outcomes (eg, goals or winning) without …

We study the problem of temporal-difference-based policy evaluation in reinforcement
learning. In particular, we analyse the use of a distributional reinforcement learning …

In recent years, brain science and neuroscience have greatly propelled the innovation of
computer science. In particular, knowledge from the neurobiology and neuropsychology of …

Current constrained reinforcement learning (RL) methods guarantee constraint satisfaction
only in expectation, which is inadequate for safety-critical decision problems. Since a …

Quantile Regression (QR) provides a way to approximate a single conditional quantile. To
have a more informative description of the conditional distribution, QR can be merged with …

A key challenge in offline reinforcement learning (RL) is how to ensure the learned offline
policy is safe, especially in safety-critical domains. In this article, we focus on learning a …

Distributional Reinforcement Learning (RL) differs from traditional RL by estimating the
distribution over returns to capture the intrinsic uncertainty of MDPs. One key challenge in …