RA-L 2021 - PRIMAL2 Paper Accepted

Our paper focusing on multi-agent pathfinding for lifelong tasks in highly structure/constrained environments has been accepted for publication in IEEE Robotics and Automation Letters (RA-L). The updated version of the paper is available from arXiv. Code and videos are linked to from within the paper. We hope you will enjoy the read/work:

• PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning – Lifelong