{"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/stabilising-experience-replay-for-deep-multi","title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning","arxiv_id":"1702.08887","date":"2017-02-28","proceeding":"ICML 2017 8","authors":["Jakob Foerster","Nantas Nardelli","Gregory Farquhar","Triantafyllos Afouras","Philip H. S. Torr","Pushmeet Kohli","Shimon Whiteson"],"abstract":"Many real-world problems, such as network packet routing and urban traffic\ncontrol, are naturally modeled as multi-agent reinforcement learning (RL)\nproblems. However, existing multi-agent RL methods typically scale poorly in\nthe problem size. Therefore, a key challenge is to translate the success of\ndeep learning on single-agent RL to the multi-agent setting. A major stumbling\nblock is that independent Q-learning, the most popular multi-agent RL method,\nintroduces nonstationarity that makes it incompatible with the experience\nreplay memory on which deep Q-learning relies. This paper proposes two methods\nthat address this problem: 1) using a multi-agent variant of importance\nsampling to naturally decay obsolete data and 2) conditioning each agent's\nvalue function on a fingerprint that disambiguates the age of the data sampled\nfrom the replay memory. Results on a challenging decentralised variant of\nStarCraft unit micromanagement confirm that these methods enable the successful\ncombination of experience replay with multi-agent RL.","url_abs":"http://arxiv.org/abs/1702.08887v3","url_pdf":"http://arxiv.org/pdf/1702.08887v3.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":"stabilising-experience-replay-for-deep-multi","repo_url":"https://github.com/MUmarJaved/MultiAgent-Distributed-Reinforcement-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"stabilising-experience-replay-for-deep-multi","repo_url":"https://github.com/anonymous1234517/code","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"stabilising-experience-replay-for-deep-multi","repo_url":"https://github.com/cts198859/deeprl_dist","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"stabilising-experience-replay-for-deep-multi","repo_url":"https://github.com/cts198859/deeprl_network","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"stabilising-experience-replay-for-deep-multi","repo_url":"https://github.com/dongchen06/macacc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent 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":"starcraft","task_name":"Starcraft"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"experience-replay","method_name":"Experience Replay"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.08887","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}