<ul><li>This paper introduces SigmaRL, an open-source, decentralized framework designed to enhance sample efficiency and generalization of multi-agent Reinforcement Learning (RL) for motion planning of connected and automated vehicles.</li><li>SigmaRL aims to address the limited generalization capacity of RL agents by proposing five strategies to design information-dense observations, focusing on general features applicable to most traffic scenarios.</li><li>The RL agents trained using SigmaRL's observation design strategies achieved training times of under one hour on a single CPU.</li><li>Evaluation results demonstrate that these RL agents can effectively zero-shot generalize, even in completely unseen traffic scenarios.</li></ul>

SigmaRL: A Sample-Efficient and Generalizable Multi-Agent Reinforcement Learning Framework for Motion Planning

Discover more