Large Scale Coordination Transfer for Cooperative Multi-Agent Reinforcement Learning

Multi-agent environments with large numbers of agents are difficult to solve due to the complexity associated with drawing sufficient samples for learning. While recent work has addressed the possibility of using transfer learning to improve sample complexities of reinforcement learning algorithms, methods for transferring knowledge in multi-agent domains across differing numbers of agents have rarely been considered. To address the bottleneck with sampling from large scale environments, we propose a joint critic structure motivated from graph convolutional networks and coordination graphs that allows for the direct transfer of parameters into environments with varying amounts of agents. We further consider fine-tuning the transferred policy and critic networks on the target domain and provide the motivation for doing so in cooperative environments where agent behavior is determined by a subset of the total population. Finally, we provide empirical results validating our claims on such environments, including popular multi-agent benchmark environments.