Recent advances in constrained reinforcement learning (RL) have endowed reinforcement
learning with certain safety guarantees. However, deploying existing constrained RL …

Constrained reinforcement learning (RL) algorithms have attracted extensive attentions
nowadays to tackle sequential decision-making problems that contain constraints defined …

Reinforcement Learning (RL) has been widely applied to many control tasks and
substantially improved the performances compared to conventional control methods in many …

Safe reinforcement learning (RL) aims to find the optimal policy and its feasible region in a
constrained optimal control problem (OCP). Ensuring feasibility and optimality …

Action-constrained reinforcement learning (RL) is a widely-used approach in various real-
world applications, such as scheduling in networked systems with resource constraints and …

Existing studies on constrained reinforcement learning (RL) may obtain a well-performing
policy in the training environment. However, when deployed in a real environment, it may …

We study continuous action reinforcement learning problems in which it is crucial that the
agent interacts with the environment only through safe policies, ie,~ policies that do not take …

Policy networks are a central feature of deep reinforcement learning (RL) algorithms for
continuous control, enabling the estimation and sampling of high-value actions. From the …

We study continuous action reinforcement learning problems in which it is crucial that the
agent interacts with the environment only through near-safe policies, ie, policies that keep …

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