MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence
This platform addresses the need for scalable environments in AI research to study collective intelligence and emergent behaviors in large populations of agents, representing a novel tool rather than an incremental improvement.
The authors introduced MAgent, a platform for many-agent reinforcement learning that supports hundreds to millions of agents, enabling the study of learning algorithms and emergent social phenomena like communication and altruism, with scalability up to one million agents on a single GPU server.
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, including communication languages, leaderships, altruism. MAgent is highly scalable and can host up to one million agents on a single GPU server. MAgent also provides flexible configurations for AI researchers to design their customized environments and agents. In this demo, we present three environments designed on MAgent and show emerged collective intelligence by learning from scratch.