Reinforcement learning (RL) has achieved tremendous success in many complex decision
making tasks. When it comes to deploying RL in the real world, safety concerns are usually …

The last half decade has seen a steep rise in the number of contributions on safe learning
methods for real-world robotic deployments from both the control and reinforcement learning …

Reinforcement Learning (RL) algorithms have found limited success beyond simulated
applications, and one main reason is the absence of safety guarantees during the learning …

Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is
beginning to show some successes in real-world scenarios. However, much of the research …

Safe reinforcement learning has been a promising approach for optimizing the policy of an
agent that operates in safety-critical applications. In this paper, we propose an algorithm …

Reinforcement Learning (RL) algorithms have had tremendous success in simulated
domains. These algorithms, however, often cannot be directly applied to physical systems …

We study the safe reinforcement learning problem using the constrained Markov decision
processes in which an agent aims to maximize the expected total reward subject to a safety …

In many sequential decision-making problems, the goal is to optimize a utility function while
satisfying a set of constraints on different utilities. This learning problem is formalized …

It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an
unknown and stochastic environment under hard constraints that require the system state …

We address the issue of safety in reinforcement learning. We pose the problem in an
episodic framework of a constrained Markov decision process. Existing results have shown …