{"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/monotonic-value-function-factorisation-for","title":"Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","arxiv_id":"2003.08839","date":"2020-03-19","proceeding":null,"authors":["Tabish Rashid","Mikayel Samvelyan","Christian Schroeder de Witt","Gregory Farquhar","Jakob Foerster","Shimon Whiteson"],"abstract":"In many real-world settings, a team of agents must coordinate its behaviour while acting in a decentralised fashion. At the same time, it is often possible to train the agents in a centralised fashion where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised policies in a centralised end-to-end fashion. QMIX employs a mixing network that estimates joint action-values as a monotonic combination of per-agent values. We structurally enforce that the joint-action value is monotonic in the per-agent values, through the use of non-negative weights in the mixing network, which guarantees consistency between the centralised and decentralised policies. To evaluate the performance of QMIX, we propose the StarCraft Multi-Agent Challenge (SMAC) as a new benchmark for deep multi-agent reinforcement learning. We evaluate QMIX on a challenging set of SMAC scenarios and show that it significantly outperforms existing multi-agent reinforcement learning methods.","url_abs":"https://arxiv.org/abs/2003.08839v2","url_pdf":"https://arxiv.org/pdf/2003.08839v2.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":"monotonic-value-function-factorisation-for","repo_url":"https://github.com/oxwhirl/pymarl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"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":"smac","task_name":"SMAC"},{"task_slug":"smac-1","task_name":"SMAC+"},{"task_slug":"starcraft","task_name":"Starcraft"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/smac-on-smac-27m-vs-30m","task":"SMAC","dataset":"SMAC 27m_vs_30m","model":"QMIX","rank_in_archive_order":8,"of":11,"metrics":{"Median Win Rate":"49"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-3s5z-vs-3s6z-1","task":"SMAC","dataset":"SMAC 3s5z_vs_3s6z","model":"QMIX","rank_in_archive_order":11,"of":13,"metrics":{"Median Win Rate":"2"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-6h-vs-8z-1","task":"SMAC","dataset":"SMAC 6h_vs_8z","model":"QMIX","rank_in_archive_order":7,"of":14,"metrics":{"Median Win Rate":"3"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-mmm2-1","task":"SMAC","dataset":"SMAC MMM2","model":"QMIX","rank_in_archive_order":10,"of":14,"metrics":{"Median Win Rate":"69"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-corridor","task":"SMAC","dataset":"SMAC corridor","model":"QMIX","rank_in_archive_order":11,"of":13,"metrics":{"Median Win Rate":"1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.08839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.08839"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/oxwhirl/pymarl","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/oxwhirl/smac","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b6994628a07e5440","entry":"QMixer","repo":"oxwhirl/pymarl","repo_kind":"official","path":"src/modules/mixers/qmix.py","file_url":"https://github.com/oxwhirl/pymarl/blob/HEAD/src/modules/mixers/qmix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b6994628a07e5440"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}