Learning Multiple Coordinated Agents under Directed Acyclic Graph Constraints

no code implementations • 13 Jul 2023 • Jaeyeon Jang, Diego Klabjan, Han Liu, Nital S. Patel, Xiuqi Li, Balakrishnan Ananthanarayanan, Husam Dauod, Tzung-Han Juang

This paper proposes a novel multi-agent reinforcement learning (MARL) method to learn multiple coordinated agents under directed acyclic graph (DAG) constraints.

Multi-agent Reinforcement Learning Scheduling