eprintid: 10070682 rev_number: 16 eprint_status: archive userid: 608 dir: disk0/10/07/06/82 datestamp: 2019-03-27 12:47:07 lastmod: 2021-10-04 00:26:31 status_changed: 2019-03-27 12:47:07 type: proceedings_section metadata_visibility: show creators_name: Zheng, L creators_name: Yang, J creators_name: Cai, H creators_name: Zhang, W creators_name: Wang, J creators_name: Yu, Y title: MAgent: A many-agent reinforcement learning platform for artificial collective intelligence ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 keywords: Reinforcement learning; multiagent system; learning environment; note: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. 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. date: 2018-02-07 date_type: published publisher: AAAI official_url: https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16459 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1629868 isbn_13: 9781577358008 lyricists_name: Wang, Jun lyricists_id: JWANG00 actors_name: Flynn, Bernadette actors_id: BFFLY94 actors_role: owner full_text_status: public publication: 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 place_of_pub: New Orleans, LA, USA pagerange: 8222-8223 event_title: 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 citation: Zheng, L; Yang, J; Cai, H; Zhang, W; Wang, J; Yu, Y; (2018) MAgent: A many-agent reinforcement learning platform for artificial collective intelligence. In: (Proceedings) 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. (pp. pp. 8222-8223). AAAI: New Orleans, LA, USA. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10070682/1/16459-77215-1-PB.pdf