MAgent: A Many-Agent Reinforcement Learning Research Platform for Artificial Collective Intelligence
Abstract
We introduce MAgent, a platform to support research and development of many-agent reinforcement learning. Unlike previous research platforms on single or multi-agent reinforcement learning, MAgent focuses on supporting the tasks and the applications that require hundreds to millions of agents. Within the interactions among a population of agents, it enables not only the study of learning algorithms for agents’ optimal polices, but more importantly, the observation and understanding of individual agent’s behaviors and social phenomena emerging from the AI society. MAgent also provides flexible configurations and a description language for AI researchers to easily design their customized environment, agents, and rewards. In this demo, we present several environments designed on MAgent and show emerged collective intelligence. Visitors can also play interactive games provided by MAgent.