Reinforcement learning agents are faced with two types of uncertainty. Epistemic … from
stochastic environments and must be accounted for in risk-sensitive applications. We highlight the …

… on deep reinforcement learning (RL), we design an adaptive car-following trajectory control
algorithm, which is called Deep Adaptive Control, to cope with different traffic risk levels… Deep …

We give an overview of recent exciting achievements of deep reinforcement learning (RL).
We discuss six core elements, six important mechanisms, and twelve applications. We start …

… risk levels … deep reinforcement learning algorithms combining with risk assessment functions
are innovatively proposed to find an optimal driving strategy with the minimum expected risk…

… This risk-seeking value can be seen as a utility for the agent under a certain risk profile
where c specifies the level of risk. For \(c>0\), the agent is risk-seeking and values risky states …

… risk optimization framework is proposed herein for building structures by developing a deep
reinforcement … and (2) a deep reinforcement learning-enabled risk optimization model for …

… This is an NP-hard problem that is crucial for risk management in many real-world … -distance
risk contagion process. To this end, we propose a novel risk-adaptive deep reinforcement …

… collision risk. The COLREGs are in place to reduce collision risk and indirectly affect the risk
level by … between the rules and the risk level, employing a measure of risk as a proxy for the …

… progress of deep reinforcement learning methods that have reached super human levels in
… are highly sensitive to economic surprise and risk aversion level. Again to ensure somehow …

… At the highest level a Deep Reinforcement Learning (DRL) agent selects among a number …
low-level agents. For the low-level agents, we use a set of Hierarchical Risk Parity (HRP) and …