Shield Decomposition for Safe Reinforcement Learning in General Partially Observable Multi-Agent Environments

Open Webpage

Daniel Melcer, Christopher Amato, Stavros Tripakis

Published: 01 Jan 2024, Last Modified: 07 Oct 2025RLJ 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Reinforcement Learning Journal (RLJ)