{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/magent-a-many-agent-reinforcement-learning","title":"MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence","arxiv_id":"1712.00600","date":"2017-12-02","proceeding":null,"authors":["Lianmin Zheng","Jiacheng Yang","Han Cai","Wei-Nan Zhang","Jun Wang","Yong Yu"],"abstract":"We introduce MAgent, a platform to support research and development of\nmany-agent reinforcement learning. Unlike previous research platforms on single\nor multi-agent reinforcement learning, MAgent focuses on supporting the tasks\nand the applications that require hundreds to millions of agents. Within the\ninteractions among a population of agents, it enables not only the study of\nlearning algorithms for agents' optimal polices, but more importantly, the\nobservation and understanding of individual agent's behaviors and social\nphenomena emerging from the AI society, including communication languages,\nleaderships, altruism. MAgent is highly scalable and can host up to one million\nagents on a single GPU server. MAgent also provides flexible configurations for\nAI researchers to design their customized environments and agents. In this\ndemo, we present three environments designed on MAgent and show emerged\ncollective intelligence by learning from scratch.","url_abs":"http://arxiv.org/abs/1712.00600v1","url_pdf":"http://arxiv.org/pdf/1712.00600v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"magent-a-many-agent-reinforcement-learning","repo_url":"https://github.com/geek-ai/MAgent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"magent-a-many-agent-reinforcement-learning","repo_url":"https://github.com/IngookJang/reinforcement-learning-TX2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"magent-a-many-agent-reinforcement-learning","repo_url":"https://github.com/hjjimmykim/SchwabRoyale","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.00600","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}