Population-based multi-agent reinforcement learning (PB-MARL) refers to a series of methods combining dynamical population selection methodologies and multi-agent reinforcement learning (MARL) algorithms. In recent years, PB-MARL has shown great potentials for non-trivial multi-agent tasks, such as RTS Games and Poker Games. This workshop will bring together researchers working at the intersection of population-based learning and multi-agent reinforcement learning. We hope it will help interested researchers outside of the field gain a high-level view of the current state of the art and potential directions for future contributions.
Welcome and Introduction, 14:00-14:05
Ming Zhou, Shanghai Jiao Tong University, 14:05-14:50
Xidong Feng, University College London, 15:15-15:50
Le Cong Dinh, University of Southampton, 15:50-16:30
Stephen McAleer, University of California, Irvine, 16:30 - 17:10
In recent years, the optimization and computational intelligence methods have achieved remarkable results in domains including robotics, games, circuit design, and large-scale scheduling engine. This workshop will bring together researchers working at the field of optimization, reinforcement learning, and evolutionary computation, and it will also cover the cutting-edge research both in academic and industrial communities. It aims to help interested researchers both inside and outside of the field gain a high-level view about the current state-of-the-art works and potential directions and applications for future.