Papers › QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

30 Mar 2018ICML 2018 7arXiv:1803.11485archive 2025-07-28

Tabish Rashid, Mikayel Samvelyan, Christian Schroeder de Witt, Gregory Farquhar, Jakob Foerster, Shimon Whiteson

In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, 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 network that estimates joint action-values as a complex non-linear combination of per-agent values that condition only on local observations. We structurally enforce that the joint-action value is monotonic in the per-agent values, which allows tractable maximisation of the joint action-value in off-policy learning, and guarantees consistency between the centralised and decentralised policies. We evaluate QMIX on a challenging set of StarCraft II micromanagement tasks, and show that QMIX significantly outperforms existing value-based multi-agent reinforcement learning methods.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (oxwhirl/pymarl) is linked to this paper; the 11 samples below come from 7 community repositories. Syntology harvested code from oxwhirl/pymarl for another paper.

oxwhirl/pymarl: Syntology's graph links these samples to Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (arXiv:2003.08839; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 11 code samples harvested from 7 repositories linked to this paper: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 7 repositories, 9 ran (8 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 4 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 9 samples that ran has no recorded date.

18 repositories listed; official and paper-mentioned ones first.

oxwhirl/pymarl officialmentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning (arXiv:2003.08839; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
TonghanWang/DOP mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
TonghanWang/NDQ mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
cathyhxh/ctds mentioned on GitHubpytorchSyntology: not harvested report
facebookresearch/benchmarl mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BenchMARL: Benchmarking Multi-Agent Reinforcement Learning (arXiv:2312.01472; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
gingkg/smac mentioned on GitHubpytorchMITSyntology: not harvested report
hhhusiyi-monash/UPDeT mentioned on GitHubpytorchSyntology: not harvested report
ifpen/wfcrl-benchmark mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jugg1er/air mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
nju-rl/acorm mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
oxwhirl/smac mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation (arXiv:2606.30966; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
puyuan1996/MARL mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
starry-sky6688/marl-algorithms mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
15534081591/QMIX mindsporeApache-2.0Syntology: 2 samples, 0 ran · 2 unverified report
2023-MindSpore-1/ms-code-221 mindsporeSyntology: not harvested report
opendilab/DI-engine pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hindsight Experience Replay (arXiv:1707.01495; that paper's own run record: 16 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified), Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified), Decision Transformer: Reinforcement Learning via Sequence Modeling (arXiv:2106.01345; that paper's own run record: 17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
ray-project/ray Syntology: not harvested report
xiuyu0000/new_papers_codes mindsporeSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran; the contract check could not run
8ran
2unverified

Licence: 6 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 7 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

TonghanWang/DOP community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
QMixer src/modules/mixers/qmix.py ran Apache-2.0 (permissive) · dbba778166e49f16 · report fixture: returned QMixer · level recorded 2026-09-22
TonghanWang/NDQ community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
QMixer src/modules/mixers/qmix.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d8b2521ad77f9ed0 · report fixture: returned QMixer · level recorded 2026-09-22
ifpen/wfcrl-benchmark community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
QMixer algos/baseline_qmix.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 7e8ae107f35df50f · report fixture: signature qvalues:Tensor/2/float, state:Tensor/2/float · returned Tensor · level recorded 2026-09-22
nju-rl/acorm community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
QMIX_Net ACORM_QMIX/algorithm/vdn_qmix.py ran no licence file found · pointer only · 44128055a06128d8 · report fixture: returned QMIX_Net · level recorded 2026-09-22
smooth in 61 papers
census: 6 implementations from 8 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 1, kind float, dtype float64
plot.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 30cf9bec8ce2ebf3 · report fixture: signature y:ndarray/1/float, radius:int/0/int, mode:str/0/str, valid_only:bool/0/bool · returned ndarray · level recorded, date not recorded
puyuan1996/MARL community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
QMIX src/policy/qmix.py ran no licence file found · pointer only · 31909679695a8aef · report fixture: returned QMIX · level recorded 2026-09-22
starry-sky6688/marl-algorithms community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
QMIX policy/qmix.py ran no licence file found · pointer only · 8d9a70332f1c598e · report fixture: returned QMIX · level recorded 2026-09-22
QMixNet policy/qmix.py ran · metamorphic tier: deterministic no licence file found · pointer only · 48fb98cde08d9bcf · report fixture: returned QMixNet · level recorded 2026-09-22
RNN in 11 papers policy/qmix.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9e0f6a55ec27b590 · report fixture: returned RNN · level recorded 2026-09-22
15534081591/QMIX community (archive-listed) 2 samples, 0 ran · 2 unverified
build_inputs src/run_310.py unverified Apache-2.0 (permissive) · a9ef2f2d8fcf96f3 · report
select_actions src/run_310.py unverified Apache-2.0 (permissive) · fc58bf6a73461826 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

6 assemblies on this paper: 6 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

6 sibling assemblies for QMIX (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for QMIX (graph method: QMIX). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 6 siblings

  1. QMixer entry · level 1 · ran · d8b2521ad77f9ed0

harvested Assembly for QMIX (graph method: QMIX). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 6 siblings

  1. QMIX entry · level 1 · ran · 8d9a70332f1c598e
  2. QMixNet model · level 1 · ran · 48fb98cde08d9bcf
  3. RNN helper · level 1 · ran · 9e0f6a55ec27b590

harvested Assembly for QMIX (graph method: QMIX). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 6 siblings

  1. QMIX entry · level 1 · ran · 31909679695a8aef
  2. QMixNet model · level 1 · ran · 48fb98cde08d9bcf
  3. RNN helper · level 1 · ran · 9e0f6a55ec27b590

harvested Assembly for QMIX (graph method: QMIX). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 6 siblings

  1. QMIX_Net entry · level 1 · ran · 44128055a06128d8

harvested Assembly for QMIX (graph method: QMIX). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 6 siblings

  1. QMixer entry · level 1 · ran · dbba778166e49f16

harvested Assembly for QMIX (graph method: QMIX). 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. QMixer entry · level 1 · ran · 7e8ae107f35df50f
  2. layer_init helper · level 1 · ran · our draft was wrong · beb42d440ccf2925

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1803.11485") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Multi-agent Reinforcement LearningReinforcement LearningReinforcement Learning (RL)SMAC+StarcraftStarcraft IIreinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
SMAC+ Def_Armored_parallel QMIX Median Win Rate 75.0 #2 of 10 Archive leaderboard report
SMAC+ Def_Armored_sequential QMIX Median Win Rate 0.0 #10 of 11 Archive leaderboard report
SMAC+ Def_Infantry_parallel QMIX Median Win Rate 95.0 #3 of 10 Archive leaderboard report
SMAC+ Def_Infantry_sequential QMIX Median Win Rate 96.9 #5 of 11 Archive leaderboard report
SMAC+ Def_Outnumbered_parallel QMIX Median Win Rate 30.0 #2 of 10 Archive leaderboard report
SMAC+ Def_Outnumbered_sequential QMIX Median Win Rate 0.0 #6 of 11 Archive leaderboard report
SMAC+ Off_Complicated_parallel QMIX Median Win Rate 0.0 #7 of 10 Archive leaderboard report
SMAC+ Off_Complicated_sequential QMIX Median Win Rate 87.5 #2 of 4 Archive leaderboard report
SMAC+ Off_Distant_parallel QMIX Median Win Rate 0.0 #7 of 10 Archive leaderboard report
SMAC+ Off_Distant_sequential QMIX Median Win Rate 93.8 #2 of 4 Archive leaderboard report
SMAC+ Off_Hard_parallel QMIX Median Win Rate 0.0 #7 of 10 Archive leaderboard report
SMAC+ Off_Hard_sequential QMIX Median Win Rate 96.9 #1 of 4 Archive leaderboard report
SMAC+ Off_Near_parallel QMIX Median Win Rate 95.0 #1 of 10 Archive leaderboard report
SMAC+ Off_Near_sequential QMIX Median Win Rate 90.6 #2 of 4 Archive leaderboard report
SMAC+ Off_Superhard_parallel QMIX Median Win Rate 0.0 #5 of 10 Archive leaderboard report
SMAC+ Off_Superhard_sequential QMIX Median Win Rate 0.0 #3 of 4 Archive leaderboard report
Starcraft II SMAC-Exp QMIX Median Win Rate % #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections