Multi-agent reinforcement learning based on estimation of others’ intentions leveraging self-policies
Masayasu FUWA, Gakuto Masuyama · The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) · 2022
The complexity of Multi-Agent Reinforcement Learning (MARL) problems increases exponentially with the number of agents. Poor scalability to the number results in limited applications of MARL to large-scale multi-agent systems.