Shield Decomposition for Safe Reinforcement Learning in General Partially Observable Multi-Agent Environments
; 4:1965−1994, 2024.
Presented at the Reinforcement Learning Conference (RLC), Amherst Massachusetts, August 9–12, 2024.
Abstract
As Reinforcement Learning is increasingly used in safety-critical systems, it is important to restrict RL agents to only take safe actions. Shielding is a promising approach to this task; however, in multi-agent domains, shielding has previously been restricted to environments where all agents observe the same information. Most real-world tasks do not satisfy this strong assumption. We discuss the theoretical foundations of multi-agent shielding in environments with general partial observability and develop a novel shielding method which is effective in such domains. Through a series of experiments, we show that agents that use our shielding method are able to safely and successfully solve a variety of RL tasks, including tasks in which prior methods cannot be applied.
BibTeX
@article{melcer2024shield,
title={Shield Decomposition for Safe Reinforcement Learning in General Partially Observable Multi-Agent Environments},
author={Melcer, Daniel and Amato, Christopher and Tripakis, Stavros},
journal={Reinforcement Learning Journal},
volume={4},
pages={1965--1994},
year={2024}
}