Safe multi-agent motion planning via filtered reinforcement learning
Abraham P. Vinod,Sleiman Safaoui,Ankush Chakrabarty,Rien Quirynen,Nobuyuki Yoshikawa,Stefano Di Cairano,Abraham P. Vinod,Sleiman Safaoui,Ankush Chakrabarty,Rien Quirynen,Nobuyuki Yoshikawa,Stefano Di Cairano
We study the problem of safe multi-agent motion planning in cluttered environments. Existing multi-agent reinforcement learning-based motion planners only provide approximate safety enforcement. We propose a safe reinforcement learning algorithm that leverages single-agent reinforcement learning for target regulation and a subsequent convex optimization-based filtering that ensures the collective ...
