{"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/multiagent-cooperation-and-competition-with","title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","arxiv_id":"1511.08779","date":"2015-11-27","proceeding":null,"authors":["Ardi Tampuu","Tambet Matiisen","Dorian Kodelja","Ilya Kuzovkin","Kristjan Korjus","Juhan Aru","Jaan Aru","Raul Vicente"],"abstract":"Multiagent systems appear in most social, economical, and political\nsituations. In the present work we extend the Deep Q-Learning Network\narchitecture proposed by Google DeepMind to multiagent environments and\ninvestigate how two agents controlled by independent Deep Q-Networks interact\nin the classic videogame Pong. By manipulating the classical rewarding scheme\nof Pong we demonstrate how competitive and collaborative behaviors emerge.\nCompetitive agents learn to play and score efficiently. Agents trained under\ncollaborative rewarding schemes find an optimal strategy to keep the ball in\nthe game as long as possible. We also describe the progression from competitive\nto collaborative behavior. The present work demonstrates that Deep Q-Networks\ncan become a practical tool for studying the decentralized learning of\nmultiagent systems living in highly complex environments.","url_abs":"http://arxiv.org/abs/1511.08779v1","url_pdf":"http://arxiv.org/pdf/1511.08779v1.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":"multiagent-cooperation-and-competition-with","repo_url":"https://github.com/NeuroCSUT/DeepMind-Atari-Deep-Q-Learner-2Player","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"multiagent-cooperation-and-competition-with","repo_url":"https://github.com/TonghanWang/DOP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multiagent-cooperation-and-competition-with","repo_url":"https://github.com/TonghanWang/NDQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multiagent-cooperation-and-competition-with","repo_url":"https://github.com/sharan-dce/coordination-pong","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"q-learning","task_name":"Q-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":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.08779","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}