AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

Multi-agent reinforcement learning (MARL) is a widely used Artificial Intelligence (AI)
technique. However, current studies and applications need to address its scalability, non …

Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the
environment. We aim to tackle a more challenging problem: learning a safe policy from an …

Artificial intelligence (AI) systems possess significant potential to drive societal progress.
However, their deployment often faces obstacles due to substantial safety concerns. Safe …

Abstract Curriculum Reinforcement Learning (CRL) aims to create a sequence of tasks,
starting from easy ones and gradually learning towards difficult tasks. In this work, we focus …

This paper presents a comprehensive benchmarking suite tailored to offline safe
reinforcement learning (RL) challenges, aiming to foster progress in the development and …

Abstract Cooperative Multi-agent Reinforcement Learning (CMARL) has shown to be
promising for many real-world applications. Previous works mainly focus on improving …

We study the tradeoff between consistency and robustness in the context of a single-
trajectory time-varying Markov Decision Process (MDP) with untrusted machine-learned …

Regardless of the particular task we want to perform in an environment, there are often
shared safety constraints we want our agents to respect. For example, regardless of whether …

In the domain of autonomous driving, the offline Reinforcement Learning (RL) approaches
exhibit notable efficacy in addressing sequential decision-making problems from offline …