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

We study sequential decision-making problems in which each agent aims to maximize the
expected total reward while satisfying a constraint on the expected total utility. We employ …

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 …

A trustworthy reinforcement learning algorithm should be competent in solving challenging
real-world problems, including {robustly} handling uncertainties, satisfying {safety} …

While machine learning can myopically reinforce social inequalities, it may also be used to
dynamically seek equitable outcomes. In this paper, we formalize long-term fairness as an …

We study the constrained reinforcement learning problem, in which an agent aims to
maximize the expected cumulative reward subject to a constraint on the expected total value …

Safe reinforcement learning is extremely challenging--not only must the agent explore an
unknown environment, it must do so while ensuring no safety constraint violations. We …

We propose an algorithm for tabular episodic reinforcement learning with constraints. We
provide a modular analysis with strong theoretical guarantees for settings with concave …

In constrained reinforcement learning (RL), a learning agent seeks to not only optimize the
overall reward but also satisfy the additional safety, diversity, or budget constraints …

We study the constrained Markov decision processes (CMDPs), in which an agent aims to
maximize the expected cumulative reward subject to a constraint on the expected total value …