MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence

Lianmin Zheng, Jiacheng Yang, Han Cai, Weinan Zhang, Jun Wang +1 more
12/2/2017
cs.LGcs.AIcs.MA

Official code: geek-ai/MAgent (1,762 stars, MIT, last commit 2022-10-22).

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, 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.

View on arXivView PDF

Code Implementations(1)

geek-ai/MAgentOfficial100%
MIT

A Platform for Many-Agent Reinforcement Learning

1,762333C, C++Nov 6, 20174 years agoMIT
deep-learningmulti-agentreinforcement-learning

Similar Papers

Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence

88% match2 repos1032019

High Performance Simulation for Scalable Multi-Agent Reinforcement Learning

88% match2022

TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning

88% match2026

Multi-Task Multi-Agent Shared Layers are Universal Cognition of Multi-Agent Coordination

87% match2023

Hypothetical Minds: Scaffolding Theory of Mind for Multi-Agent Tasks with Large Language Models

87% match1 repo642024

GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-Critic

87% match2024

Cite this paper

@article{zheng2017magent,
  title  = {MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence},
  author = {Lianmin Zheng and Jiacheng Yang and Han Cai and Weinan Zhang and Jun Wang and Yong Yu},
  year   = {2017},
  eprint = {1712.00600},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1712.00600}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1712.00600.svg)](https://codeofpaper.com/paper/1712.00600)

Discussion