{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"syntology_url":"https://syntology.ai/paper/1702.08887","atlas_url":"https://app.syntology.ai/?focus=1702.08887","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1702.08887"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1702.08887\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1702.08887"},"call":"get_concepts_for_paper(arxiv_id=\"1702.08887\")"}],"by_repo":[{"repo":"MUmarJaved/MultiAgent-Distributed-Reinforcement-Learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"anonymous1234517/code","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"cts198859/deeprl_dist","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"cts198859/deeprl_network","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2004.01339"],"harvested_for_calls":[{"arxiv_id":"2004.01339","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.01339"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.01339\")"}]},{"repo":"dongchen06/macacc","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"176e87335c2649c9e1bf329d7b317a4da482b30639c5cad9578f5737865cd0be","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}