Papers › The StarCraft Multi-Agent Challenge

The StarCraft Multi-Agent Challenge

11 Feb 2019arXiv:1902.04043archive 2025-07-28

Mikayel Samvelyan, Tabish Rashid, Christian Schroeder de Witt, Gregory Farquhar, Nantas Nardelli, Tim G. J. Rudner, Chia-Man Hung, Philip H. S. Torr, Jakob Foerster, Shimon Whiteson

In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents must learn to coordinate their behaviour while conditioning only on their private observations. This is an attractive research area since such problems are relevant to a large number of real-world systems and are also more amenable to evaluation than general-sum problems. Standardised environments such as the ALE and MuJoCo have allowed single-agent RL to move beyond toy domains, such as grid worlds. However, there is no comparable benchmark for cooperative multi-agent RL. As a result, most papers in this field use one-off toy problems, making it difficult to measure real progress. In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap. SMAC is based on the popular real-time strategy game StarCraft II and focuses on micromanagement challenges where each unit is controlled by an independent agent that must act based on local observations. We offer a diverse set of challenge maps and recommendations for best practices in benchmarking and evaluations. We also open-source a deep multi-agent RL learning framework including state-of-the-art algorithms. We believe that SMAC can provide a standard benchmark environment for years to come. Videos of our best agents for several SMAC scenarios are available at: https://youtu.be/VZ7zmQ_obZ0.

PaperPDFCodeCode Syntology ran

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 repositories (oxwhirl/pymarl, oxwhirl/smac) is linked to this paper; the 15 samples below come from 8 community repositories. Syntology harvested code from oxwhirl/pymarl for another paper; from oxwhirl/smac 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. oxwhirl/smac: 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.

Syntology 15 code samples harvested from 8 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 15 samples from 8 repositories, 10 ran (4 with no instrument failure; 6 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 5 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 6 of the 10 samples that ran have no recorded date.

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

oxwhirl/pymarl officialmentioned in papermentioned 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
oxwhirl/smac officialmentioned in papermentioned 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
Denys88/rl_games mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality (arXiv:2210.13702; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
Lamperougeyxy/GHQ mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ailabdsunipi/pymarlzooplus mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex... (arXiv:2502.04773; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 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
dtabas/epymarl mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks (arXiv:2006.07869; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
gingkg/smac mentioned on GitHubpytorchMITSyntology: not harvested report
hahayonghuming/VDACs mentioned on GitHubpytorchMITSyntology: not harvested report
jk96491/C-COMA mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 0 ran · 3 unverified report
jk96491/SMAC mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jugg1er/air mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
kcorder/qmix_variants mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
kinalmehta/epymarl mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
ling-pan/res mentioned on GitHubpytorchApache-2.0Syntology: 1 sample, 0 ran · 1 unverified report
mahi97/XQMIX mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
osilab-kaist/smac_exp mentioned on GitHubpytorchSyntology: not harvested report
osilab-kaist/smac_plus mentioned on GitHubpytorchSyntology: not harvested report
oxwhirl/facmac mentioned on GitHubpytorchSyntology: not harvested report
oxwhirl/smacv2 mentioned on GitHubSyntology: 1 sample, 0 ran · 1 unverified report
simsimiSION/pymarl-algorithm-extension-via-starcraft mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
uoe-agents/epymarl mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
wendelinboehmer/dcg mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
starry-sky6688/marl-algorithms pytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified 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

15 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 5 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.

6ran · our draft was wrong
4ran
5unverified

Licence: 14 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 8 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. 3 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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.

Lamperougeyxy/GHQ community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
args_sanity_check src-GHQ/hetero_run.py ran MIT (permissive) here; the stored copy is pointer only · 012625dd7922e3c6 · report fixture: signature config:dict/0/?, _log:Logger/0/? · returned dict · level recorded 2026-09-25
jk96491/C-COMA community (archive-listed) 3 samples, 0 ran · 3 unverified
config_copy src/config_util.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 6da83f6c43f19bcd · report
get_config in 203 papers src/config_util.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 97de3c09702583fa · report
recursive_dict_update src/config_util.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 29b55b98f851c566 · report
jk96491/SMAC community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
process_batch in 31 papers offpg_run.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 8167e3248b280556 · report fixture: signature batch:SimpleBatch/0/?, args:SimpleArgs/0/? · returned SimpleBatch · level recorded 2026-09-24
kcorder/qmix_variants community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_run_cmds gen_run_configs.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · cc14e47211ac4bfe · report fixture: signature config:dict/0/? · returned list · level recorded 2026-09-24
onehot_from_logits in 10 papers src/components/action_selectors.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · d2a8ffa31f7e13c8 · report fixture: signature logits:Tensor/2/float, avail_logits:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-24
ling-pan/res community (archive-listed) 1 sample, 0 ran · 1 unverified
int2onehot src/envs/mpe_env.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 5e82021904c004bf · report
oxwhirl/smacv2 community (archive-listed) 1 sample, 0 ran · 1 unverified
get_distribution in 8 papers smacv2/env/starcraft2/distributions.py unverified MIT (permissive) · 931274a62c01dbc3 · report
uoe-agents/epymarl community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
extract_alg_name_from_config in 5 papers plot_results.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · fa9a1eda0ac523d2 · report fixture: signature config:dict/0/? · returned str · level recorded, date not recorded
extract_env_name_from_config in 5 papers plot_results.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · cf0832c848510d11 · report fixture: signature config:dict/0/? · returned str · level recorded, date not recorded
load_results in 82 papers plot_results.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 73de3ace29add240 · report fixture: signature path:str/0/str, metric:str/0/str · returned defaultdict · level recorded, date not recorded
starry-sky6688/marl-algorithms community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
get_centralv_args common/arguments.py ran · our draft was wrong no licence file found · pointer only · b19a31174c009d56 · report fixture: signature args:Args/0/? · returned Args · level recorded, date not recorded
get_coma_args common/arguments.py ran · our draft was wrong no licence file found · pointer only · b45504dbf41a0cc7 · report fixture: signature args:Args/0/? · returned Args · level recorded, date not recorded
get_mixer_args common/arguments.py ran · our draft was wrong no licence file found · pointer only · 3bb5b43703ab9da4 · report fixture: signature args:SimpleArgs/0/? · returned SimpleArgs · level recorded, date not recorded

Tasks

BenchmarkingMuJoCoMulti-agent Reinforcement LearningReal-Time Strategy GamesReinforcement LearningReinforcement Learning (RL)SMACSMAC+StarcraftStarcraft II

Datasets

Introduced by this paper, per the archive.

SMAC

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
SMAC SMAC 27m_vs_30m QMIX Median Win Rate 49 #7 of 11 Archive leaderboard report
SMAC SMAC 27m_vs_30m Heuristic Median Win Rate 0 #11 of 11 Archive leaderboard report
SMAC SMAC 3s5z_vs_3s6z VDN Median Win Rate 2 #10 of 13 Archive leaderboard report
SMAC SMAC 3s5z_vs_3s6z IQL Median Win Rate 0 #12 of 13 Archive leaderboard report
SMAC SMAC 3s5z_vs_3s6z Heuristic Median Win Rate 0 #13 of 13 Archive leaderboard report
SMAC SMAC 6h_vs_8z QMIX Median Win Rate 3 #6 of 14 Archive leaderboard report
SMAC SMAC 6h_vs_8z IQL Median Win Rate 0 #11 of 14 Archive leaderboard report
SMAC SMAC 6h_vs_8z VDN Median Win Rate 0 #12 of 14 Archive leaderboard report
SMAC SMAC 6h_vs_8z Heuristic Median Win Rate 0 #13 of 14 Archive leaderboard report
SMAC SMAC MMM2 QMIX Median Win Rate 69 #9 of 14 Archive leaderboard report
SMAC SMAC MMM2 VDN Median Win Rate 1 #12 of 14 Archive leaderboard report
SMAC SMAC MMM2 IQL Median Win Rate 0 #13 of 14 Archive leaderboard report
SMAC SMAC MMM2 Heuristic Median Win Rate 0 #14 of 14 Archive leaderboard report
SMAC SMAC corridor QMIX Median Win Rate 1 #10 of 13 Archive leaderboard report
SMAC SMAC corridor IQL Median Win Rate 0 #12 of 13 Archive leaderboard report
SMAC SMAC corridor Heuristic Median Win Rate 0 #13 of 13 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