{"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/qmix-monotonic-value-function-factorisation","title":"QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning","arxiv_id":"1803.11485","date":"2018-03-30","proceeding":"ICML 2018 7","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 their behaviour\nwhile acting in a decentralised way. At the same time, it is often possible to\ntrain the agents in a centralised fashion in a simulated or laboratory setting,\nwhere global state information is available and communication constraints are\nlifted. Learning joint action-values conditioned on extra state information is\nan attractive way to exploit centralised learning, but the best strategy for\nthen extracting decentralised policies is unclear. Our solution is QMIX, a\nnovel value-based method that can train decentralised policies in a centralised\nend-to-end fashion. QMIX employs a network that estimates joint action-values\nas a complex non-linear combination of per-agent values that condition only on\nlocal observations. We structurally enforce that the joint-action value is\nmonotonic in the per-agent values, which allows tractable maximisation of the\njoint action-value in off-policy learning, and guarantees consistency between\nthe centralised and decentralised policies. We evaluate QMIX on a challenging\nset of StarCraft II micromanagement tasks, and show that QMIX significantly\noutperforms existing value-based multi-agent reinforcement learning methods.","url_abs":"http://arxiv.org/abs/1803.11485v2","url_pdf":"http://arxiv.org/pdf/1803.11485v2.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":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/oxwhirl/pymarl","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/TonghanWang/DOP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/TonghanWang/NDQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/cathyhxh/ctds","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/facebookresearch/benchmarl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/gingkg/smac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/hhhusiyi-monash/UPDeT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/ifpen/wfcrl-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/jugg1er/air","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/nju-rl/acorm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/oxwhirl/smac","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/puyuan1996/MARL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/starry-sky6688/marl-algorithms","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/15534081591/QMIX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/2023-MindSpore-1/ms-code-221/tree/main/qmix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/qmix.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/ray-project/ray/tree/master/rllib","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"qmix-monotonic-value-function-factorisation","repo_url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/qmix","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","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-1","task_name":"SMAC+"},{"task_slug":"starcraft","task_name":"Starcraft"},{"task_slug":"starcraft-ii","task_name":"Starcraft II"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/smac-on-smac-def-armored-parallel","task":"SMAC+","dataset":"Def_Armored_parallel","model":"QMIX","rank_in_archive_order":2,"of":10,"metrics":{"Median Win Rate":"75.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-def-armored-sequential","task":"SMAC+","dataset":"Def_Armored_sequential","model":"QMIX","rank_in_archive_order":10,"of":11,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-def-infantry-parallel","task":"SMAC+","dataset":"Def_Infantry_parallel","model":"QMIX","rank_in_archive_order":3,"of":10,"metrics":{"Median Win Rate":"95.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-def-infantry-sequential","task":"SMAC+","dataset":"Def_Infantry_sequential","model":"QMIX","rank_in_archive_order":5,"of":11,"metrics":{"Median Win Rate":"96.9"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-def-outnumbered-parallel","task":"SMAC+","dataset":"Def_Outnumbered_parallel","model":"QMIX","rank_in_archive_order":2,"of":10,"metrics":{"Median Win Rate":"30.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-def-outnumbered-sequential","task":"SMAC+","dataset":"Def_Outnumbered_sequential","model":"QMIX","rank_in_archive_order":6,"of":11,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-complicated-parallel","task":"SMAC+","dataset":"Off_Complicated_parallel","model":"QMIX","rank_in_archive_order":7,"of":10,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-complicated-sequential","task":"SMAC+","dataset":"Off_Complicated_sequential","model":"QMIX","rank_in_archive_order":2,"of":4,"metrics":{"Median Win Rate":"87.5"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-distant-parallel","task":"SMAC+","dataset":"Off_Distant_parallel","model":"QMIX","rank_in_archive_order":7,"of":10,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-distant-sequential","task":"SMAC+","dataset":"Off_Distant_sequential","model":"QMIX","rank_in_archive_order":2,"of":4,"metrics":{"Median Win Rate":"93.8"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-hard-parallel","task":"SMAC+","dataset":"Off_Hard_parallel","model":"QMIX","rank_in_archive_order":7,"of":10,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-hard-sequential","task":"SMAC+","dataset":"Off_Hard_sequential","model":"QMIX","rank_in_archive_order":1,"of":4,"metrics":{"Median Win Rate":"96.9"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-near-parallel","task":"SMAC+","dataset":"Off_Near_parallel","model":"QMIX","rank_in_archive_order":1,"of":10,"metrics":{"Median Win Rate":"95.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-near-sequential","task":"SMAC+","dataset":"Off_Near_sequential","model":"QMIX","rank_in_archive_order":2,"of":4,"metrics":{"Median Win Rate":"90.6"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-superhard-parallel","task":"SMAC+","dataset":"Off_Superhard_parallel","model":"QMIX","rank_in_archive_order":5,"of":10,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/smac-on-smac-off-superhard-sequential","task":"SMAC+","dataset":"Off_Superhard_sequential","model":"QMIX","rank_in_archive_order":3,"of":4,"metrics":{"Median Win Rate":"0.0"},"uses_additional_data":false},{"leaderboard":"/sota/starcraft-ii-on-smac","task":"Starcraft II","dataset":"SMAC-Exp","model":"QMIX","rank_in_archive_order":1,"of":1,"metrics":{"Median Win Rate":"%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.11485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.11485"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oxwhirl/pymarl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oxwhirl/smac","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-221/tree/main/qmix","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nju-rl/acorm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ray-project/ray/tree/master/rllib","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/puyuan1996/MARL","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/starry-sky6688/marl-algorithms","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/15534081591/QMIX","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/qmix.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TonghanWang/DOP","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/TonghanWang/NDQ","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gingkg/smac","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hhhusiyi-monash/UPDeT","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ifpen/wfcrl-benchmark","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jugg1er/air","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xiuyu0000/new_papers_codes/tree/main/qmix","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/benchmarl","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cathyhxh/ctds","reach":{"status":"ok"}}],"summary":{"ran":8,"ran_fixture":1,"unverified":2},"by_repo_kind":{"listed":{"samples":11,"ran":9,"repositories":7}},"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":6,"samples":[{"code_sha256_prefix":"8d9a70332f1c598e","entry":"QMIX","repo":"starry-sky6688/marl-algorithms","repo_kind":"listed","path":"policy/qmix.py","file_url":"https://github.com/starry-sky6688/marl-algorithms/blob/HEAD/policy/qmix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d9a70332f1c598e"}},{"code_sha256_prefix":"31909679695a8aef","entry":"QMIX","repo":"puyuan1996/MARL","repo_kind":"listed","path":"src/policy/qmix.py","file_url":"https://github.com/puyuan1996/MARL/blob/HEAD/src/policy/qmix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"31909679695a8aef"}},{"code_sha256_prefix":"44128055a06128d8","entry":"QMIX_Net","repo":"nju-rl/acorm","repo_kind":"listed","path":"ACORM_QMIX/algorithm/vdn_qmix.py","file_url":"https://github.com/nju-rl/acorm/blob/HEAD/ACORM_QMIX/algorithm/vdn_qmix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44128055a06128d8"}},{"code_sha256_prefix":"48fb98cde08d9bcf","entry":"QMixNet","repo":"starry-sky6688/marl-algorithms","repo_kind":"listed","path":"policy/qmix.py","file_url":"https://github.com/starry-sky6688/marl-algorithms/blob/HEAD/policy/qmix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48fb98cde08d9bcf"}},{"code_sha256_prefix":"d8b2521ad77f9ed0","entry":"QMixer","repo":"TonghanWang/NDQ","repo_kind":"listed","path":"src/modules/mixers/qmix.py","file_url":"https://github.com/TonghanWang/NDQ/blob/HEAD/src/modules/mixers/qmix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d8b2521ad77f9ed0"}},{"code_sha256_prefix":"dbba778166e49f16","entry":"QMixer","repo":"TonghanWang/DOP","repo_kind":"listed","path":"src/modules/mixers/qmix.py","file_url":"https://github.com/TonghanWang/DOP/blob/HEAD/src/modules/mixers/qmix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dbba778166e49f16"}},{"code_sha256_prefix":"7e8ae107f35df50f","entry":"QMixer","repo":"ifpen/wfcrl-benchmark","repo_kind":"listed","path":"algos/baseline_qmix.py","file_url":"https://github.com/ifpen/wfcrl-benchmark/blob/HEAD/algos/baseline_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":"7e8ae107f35df50f"}},{"code_sha256_prefix":"9e0f6a55ec27b590","entry":"RNN","repo":"starry-sky6688/marl-algorithms","repo_kind":"listed","path":"policy/qmix.py","file_url":"https://github.com/starry-sky6688/marl-algorithms/blob/HEAD/policy/qmix.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e0f6a55ec27b590"}},{"code_sha256_prefix":"30cf9bec8ce2ebf3","entry":"smooth","repo":"nju-rl/acorm","repo_kind":"listed","path":"plot.py","file_url":"https://github.com/nju-rl/acorm/blob/HEAD/plot.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"30cf9bec8ce2ebf3"}},{"code_sha256_prefix":"a9ef2f2d8fcf96f3","entry":"build_inputs","repo":"15534081591/QMIX","repo_kind":"listed","path":"src/run_310.py","file_url":"https://github.com/15534081591/QMIX/blob/HEAD/src/run_310.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a9ef2f2d8fcf96f3"}},{"code_sha256_prefix":"fc58bf6a73461826","entry":"select_actions","repo":"15534081591/QMIX","repo_kind":"listed","path":"src/run_310.py","file_url":"https://github.com/15534081591/QMIX/blob/HEAD/src/run_310.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc58bf6a73461826"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}