Papers › Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

7 Jun 2017NeurIPS 2017 12arXiv:1706.02275archive 2025-07-28

Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb, Pieter Abbeel, Igor Mordatch

We explore deep reinforcement learning methods for multi-agent domains. We begin by analyzing the difficulty of traditional algorithms in the multi-agent case: Q-learning is challenged by an inherent non-stationarity of the environment, while policy gradient suffers from a variance that increases as the number of agents grows. We then present an adaptation of actor-critic methods that considers action policies of other agents and is able to successfully learn policies that require complex multi-agent coordination. Additionally, we introduce a training regimen utilizing an ensemble of policies for each agent that leads to more robust multi-agent policies. We show the strength of our approach compared to existing methods in cooperative as well as competitive scenarios, where agent populations are able to discover various physical and informational coordination strategies.

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

The archive's official repository (openai/multiagent-particle-envs) was not harvested; the 142 samples below come from 29 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository.

Syntology 143 code samples: 142 from 29 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 143: 75 ran (of which 54 constructed an object rather than computing a result; 68 with no instrument failure: 2 honoured, 0 violated, 66 with no contract checked; 7 where Syntology's instrument failed) · 68 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 142 samples from 29 repositories, 74 ran (67 with no instrument failure; 7 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

openai/multiagent-particle-envs officialmentioned in papermentioned on GitHubSyntology: not harvested report
Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Ah31/maddpg_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
AleXander-Tsui/MPE mentioned on GitHubSyntology: not harvested report
Chan1998/MAAC mentioned on GitHubpytorchSyntology: 11 samples, 5 ran (2 instrument-failed) · 6 unverified report
EyaRhouma/collaboration-competition-MADDPG mentioned on GitHubpytorchSyntology: 5 samples, 2 ran (0 instrument-failed) · 3 unverified report
JinTanda/MADDPG_env mentioned on GitHubSyntology: not harvested report
JohannesAck/MATD3implementation mentioned on GitHubtfSyntology: not harvested report
JohannesAck/tf2multiagentrl mentioned on GitHubtfSyntology: not harvested report
LXYYY/multiagent-particle-envs mentioned on GitHubSyntology: not harvested report
MrDaubinet/collaboration-and-competition mentioned on GitHubpytorchSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
NeuroCSUT/intentions mentioned on GitHubtfSyntology: not harvested report
RL-WFU/multi_agent_attack mentioned on GitHubtfSyntology: not harvested report
SihongHo/multiagent-particle-envs mentioned on GitHubSyntology: not harvested report
SintolRTOS/multi-agent_Example mentioned on GitHubSyntology: not harvested report
Steven-Ho/multiagent-particle-envs mentioned on GitHubSyntology: not harvested report
Stippler/cow-simulator mentioned on GitHubpytorchSyntology: not harvested report
Yutongamber/MADDPG mentioned on GitHubpytorchSyntology: 8 samples, 5 ran (4 instrument-failed) · 3 unverified report
Zorrorulz/MultiAgentDDPG-Tennis mentioned on GitHubSyntology: not harvested report
anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning mentioned on GitHubpytorchSyntology: 11 samples, 8 ran (0 instrument-failed) · 3 unverified report
baicenxiao/shaping-advice mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Guidance Rewards with Trajectory-space Smoothing (arXiv:2010.12718; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
baoqianwang/iros22_darl1n mentioned on GitHubtfSyntology: 34 samples, 4 ran (1 instrument-failed) · 30 unverified report
baradist/multiagent-particle-envs mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
biemann/Collaboration-and-Competition mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
biorobotics/PRD_environments mentioned on GitHubSyntology: not harvested report
bonniesjli/MADDPG_Tennis mentioned on GitHubpytorchSyntology: not harvested report
bonniesjli/MADDPG_Tennis_UnityML mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
caslab-vt/SARNet mentioned on GitHubtfSyntology: not harvested report
cyanrain7/trpo-in-marl mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
cyoon1729/Multi-agent-reinforcement-learning mentioned on GitHubpytorchSyntology: not harvested report
darshil333/CSE574 mentioned on GitHubSyntology: not harvested report
debajit15kgp/multiagent-envs mentioned on GitHubSyntology: not harvested report
dtabas/multiagent-particle-envs mentioned on GitHubSyntology: 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/multiagent-particle-envs mentioned on GitHubSyntology: not harvested report
goldbattle/snakes_mal mentioned on GitHubtfSyntology: not harvested report
google/maddpg-replication mentioned on GitHubtfSyntology: not harvested report
hepengli/multiagent-particle-envs mentioned on GitHubtfSyntology: not harvested report
isp1tze/MAProj mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
jansenkeith501/CS295-MADDPG mentioned on GitHubSyntology: not harvested report
jiayu-ch15/MPE-for-curriculum-learning mentioned on GitHubSyntology: not harvested report
jingdic/rgmcomm mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
johannesharmse/multi_agent_RL mentioned on GitHubSyntology: 1 sample, 0 ran · 1 unverified report
jyqhahah/rl_maddpg_matd3 mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
kargarisaac/macrpo mentioned on GitHubpytorchSyntology: not harvested report
karishnu/tf-agents-multi-particle-envs mentioned on GitHubtfSyntology: not harvested report
krasing/DRLearningCollaboration mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
ksajan/DDPG-MAPE mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
lachisis/multiagent-particle-envs mentioned on GitHubSyntology: not harvested report
madhur-tandon/RL-Project mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous control with deep reinforcement learning (arXiv:1509.02971; that paper's own run record: 163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified); nothing checks that they implement this paper's method. report
madras-simulator/Multi-Agent-Particle-Environment mentioned on GitHubtfSyntology: not harvested report
marwanihab/RL_Tag_Game mentioned on GitHubpytorchSyntology: not harvested report
marwanihab/RL_Testing_Noise_ASRN mentioned on GitHubtfSyntology: not harvested report
mauricemager/multiagent-robot mentioned on GitHubtfSyntology: 2 samples, 0 ran · 2 unverified report
morning9393/HAPPO-HATRPO mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
openai/maddpg mentioned on GitHubtfSyntology: not harvested report
petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
pr-shukla/maddpg-keras mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
qi-pang/mdpfuzz mentioned on GitHubSyntology: not harvested report
quantumiracle/mars mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in... (arXiv:2207.08894; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
rainandwind1/MADDPG-reconstruct mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
rainandwind1/MERL mentioned on GitHubpytorchSyntology: not harvested report
rainandwind1/Maddpg_multiagent mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
rallen10/multiagent-particle-envs mentioned on GitHubSyntology: not harvested report
raoshashank/Tennis-with-MADDPG mentioned on GitHubpytorchSyntology: not harvested report
schroederdewitt/multiagent-particle-envs mentioned on GitHubSyntology: not harvested report
semitable/multiagent-particle-envs mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and... (arXiv:2505.05262; that paper's own run record: 6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
shariqiqbal2810/maddpg-pytorch mentioned on GitHubpytorchSyntology: not harvested report
shariqiqbal2810/multiagent-particle-envs mentioned on GitHubSyntology: not harvested report
sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous control with deep reinforcement learning (arXiv:1509.02971; that paper's own run record: 163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified); nothing checks that they implement this paper's method. report
starry-sky6688/MADDPG mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
thechrisyoon08/Multi-agent-reinforcement-learning mentioned on GitHubpytorchSyntology: not harvested report
thechrisyoon08/marl mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
tkarr21/multagent-particle-envs mentioned on GitHubSyntology: not harvested report
tkarr21/multiagent-particle-envs mentioned on GitHubSyntology: not harvested report
wsjeon/multiagent-particle-envs-maac mentioned on GitHubSyntology: not harvested report
wsjeon/multiagent-particle-envs-v2 mentioned on GitHubSyntology: not harvested report
xuehy/pytorch-maddpg mentioned on GitHubtfSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
yannbouteiller/gym-airsimdroneracinglab mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Real-Time Reinforcement Learning (arXiv:1911.04448; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
zoeyuchao/MPE-pytorch mentioned on GitHubpytorchSyntology: not harvested report
zoeyuchao/MPEnew-pytorch mentioned on GitHubpytorchSyntology: not harvested report
zowiezhang/stas mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
ray-project/ray Syntology: 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

143 samples harvested: 75 ran (of which 54 constructed an object rather than computing a result; 68 with no instrument failure: 2 honoured, 0 violated, 66 with no contract checked; 7 where Syntology's instrument failed) · 68 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.

2ran · honoured contract
6ran · our draft was wrong
1ran; the contract check could not run
66ran
68unverified

Licence: 99 of the 143 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 29 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. 1 sample is listed last, in a group without a repository. “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”. For 20 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

Abdelhamid-bouzid/Multi-Agent-Deep-Deterministic-Policy-Gradient community (archive-listed) 1 sample, 0 ran · 1 unverified
MADDPG maddpg.py unverified no licence file found · pointer only · 6c6569c6b5d38959 · report
Ah31/maddpg_pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Actor in 68 papers MADDPG_model.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · e0a77db60f82cb02 · report fixture: signature state:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Chan1998/MAAC community (archive-listed) 11 samples, 5 ran (2 instrument-failed) · 6 unverified
AttentionCritic algorithms/attention_sac.py ran · metamorphic tier: deterministic licence not identified · pointer only · 23a16fcf13d93070 · report fixture: returned AttentionCritic · level recorded 2026-09-22
BasePolicy in 8 papers algorithms/attention_sac.py ran · metamorphic tier: deterministic licence not identified · pointer only · e3579cc107de4c0a · report fixture: returned BasePolicy · level recorded 2026-09-22
DiscretePolicy algorithms/attention_sac.py ran licence not identified · pointer only · b4fe457a99be3144 · report fixture: signature obs:Tensor/2/float, sample:bool/0/bool, return_all_probs:bool/0/bool, return_log_pi:bool/0/bool, regularize:bool/0/bool, return_entropy:bool/0/bool · returned list · level recorded 2026-09-24
categorical_sample in 5 papers algorithms/attention_sac.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 8a12d52820205fa8 · report fixture: signature probs:Tensor/2/float, use_cuda:bool/0/bool · returned tuple · level recorded 2026-09-22
onehot_from_logits in 10 papers algorithms/attention_sac.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 5290a0543b38c4dc · report fixture: signature logits:Tensor/2/float, eps:float/0/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
AttentionAgent algorithms/attention_sac.py unverified licence not identified · pointer only · 5e7a8abdf83466de · report
AttentionSAC algorithms/attention_sac.py unverified licence not identified · pointer only · 92865550d0fc369e · report
disable_gradients algorithms/attention_sac.py unverified licence not identified · pointer only · 34bbc966346baa78 · report
enable_gradients algorithms/attention_sac.py unverified licence not identified · pointer only · 8e93ecfbcd3abb77 · report
hard_update algorithms/attention_sac.py unverified licence not identified · pointer only · e6250f15677e1203 · report
soft_update in 8 papers algorithms/attention_sac.py unverified licence not identified · pointer only · f36b207d39a0f07a · report
EyaRhouma/collaboration-competition-MADDPG community (archive-listed) 5 samples, 2 ran (0 instrument-failed) · 3 unverified
ActorModel MADDPG_agent.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7153bd2279c31cfb · report fixture: signature state:Tensor/2/float · returned Tensor · level recorded 2026-09-22
CriticModel MADDPG_agent.py ran · metamorphic tier: invariant no licence file found · pointer only · 1e89d38fb0c5b84b · report fixture: signature states:Tensor/2/float, actions:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Actor_Critic_Models MADDPG_agent.py unverified no licence file found · pointer only · 1b5ce00b5c4ba8e0 · report
MADDPG MADDPG_agent.py unverified no licence file found · pointer only · 8064ffc41e0e0c2e · report
ReplayBuffer in 33 papers MADDPG_agent.py unverified no licence file found · pointer only · 0fe6e65cdf5950a9 · report
MrDaubinet/collaboration-and-competition community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
Actor in 68 papers maddpg.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 147d57177bbffdd9 · report fixture: returned Actor · level recorded 2026-09-22
Critic in 60 papers maddpg.py ran · metamorphic tier: deterministic no licence file found · pointer only · 6c1f59af0972c70e · report fixture: returned Critic · level recorded 2026-09-22
OUNoise in 6 papers maddpg.py ran no licence file found · pointer only · db3bd13d21d6150c · report fixture: returned OUNoise · level recorded 2026-09-22
ReplayBuffer in 33 papers maddpg.py ran no licence file found · pointer only · ae26aa48075ee6cb · report fixture: returned ReplayBuffer · level recorded 2026-09-22
Agent in 42 papers maddpg.py unverified no licence file found · pointer only · 5d2d3b9ff319eb0d · report
MADDPG maddpg.py unverified no licence file found · pointer only · 6551e7add10520be · report
Yutongamber/MADDPG community (archive-listed) 8 samples, 5 ran (4 instrument-failed) · 3 unverified
MLPNetwork in 6 papers maddpg-pytorch/algorithms/maddpg.py ran · metamorphic tier: invariant MIT (permissive) · d91c262ff01c1192 · report fixture: signature X:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gumbel_softmax in 82 papers
census: 19 implementations from 20 papers, 12 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
maddpg-pytorch/algorithms/maddpg.py ran · our draft was wrong fingerprinted MIT (permissive) · 57d033c0c861f3d0 · report fixture: signature logits:Tensor/2/float, temperature:float/0/float, hard:bool/0/bool · returned Tensor · level recorded 2026-09-22
gumbel_softmax_sample in 49 papers
census: 14 implementations from 16 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
maddpg-pytorch/algorithms/maddpg.py ran · our draft was wrong fingerprinted MIT (permissive) · 6697676fd57aebe3 · report fixture: signature logits:Tensor/2/float, temperature:float/0/float · returned Tensor · level recorded 2026-09-22
onehot_from_logits in 10 papers maddpg-pytorch/algorithms/maddpg.py ran · our draft was wrong fingerprinted MIT (permissive) · f925a8c266bb2532 · report fixture: signature logits:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
sample_gumbel in 62 papers maddpg-pytorch/algorithms/maddpg.py ran · our draft was wrong MIT (permissive) · 43c7e814609746ee · report fixture: signature shape:tuple/1/int, eps:float/0/float, tens_type:tensortype/0/float · returned Tensor · level recorded 2026-09-22
DDPGAgent in 5 papers maddpg-pytorch/algorithms/maddpg.py unverified MIT (permissive) · 23ccb70277ce98c1 · report
MADDPG maddpg-pytorch/algorithms/maddpg.py unverified MIT (permissive) · 05a2c85c2c068627 · report
average_gradients in 20 papers maddpg-pytorch/algorithms/maddpg.py unverified MIT (permissive) · a3e542c9d6910a27 · report
anonymous-iclr22/trust-region-in-multi-agent-reinforcement-learning community (archive-listed) 11 samples, 8 ran (0 instrument-failed) · 3 unverified
ACTLayer algorithms/happo_policy.py ran fingerprinted MIT (permissive) · 788933ff608baaea · report fixture: returned ACTLayer · level recorded 2026-09-22
Bernoulli in 7 papers algorithms/happo_policy.py ran MIT (permissive) · ce4cd71349aedb12 · report fixture: returned Bernoulli · level recorded 2026-09-22
DiagGaussian algorithms/happo_policy.py ran MIT (permissive) · 6072c4350e278037 · report fixture: returned DiagGaussian · level recorded 2026-09-22
FixedBernoulli algorithms/happo_policy.py ran MIT (permissive) · a48b952a1d356122 · report fixture: returned FixedBernoulli · level recorded 2026-09-22
FixedNormal algorithms/happo_policy.py ran MIT (permissive) · 2430b3c71fa829d4 · report fixture: returned FixedNormal · level recorded 2026-09-22
MLPBase algorithms/happo_policy.py ran fingerprinted MIT (permissive) · eb97113b662895e7 · report fixture: returned MLPBase · level recorded 2026-09-22
MLPLayer in 15 papers algorithms/happo_policy.py ran MIT (permissive) · 052cdd66a800bf26 · report fixture: returned MLPLayer · level recorded 2026-09-22
RNNLayer algorithms/happo_policy.py ran MIT (permissive) · ff5a06e4902f81ab · report fixture: returned RNNLayer · level recorded 2026-09-22
Actor in 68 papers algorithms/happo_policy.py unverified MIT (permissive) · fe0a30f4af252b51 · report
Critic in 60 papers algorithms/happo_policy.py unverified MIT (permissive) · 598a59b21df91031 · report
HAPPO_Policy algorithms/happo_policy.py unverified MIT (permissive) · a78bf4c700ca5bb9 · report
baoqianwang/iros22_darl1n community (archive-listed) 34 samples, 4 ran (1 instrument-failed) · 30 unverified
PlacholderTfInput maddpg_o/maddpg_local/trainer/maddpg.py ran fingerprinted no licence file found · pointer only · bab2a198c923111d · report fixture: signature data:Tensor/2/float · returned dict · level recorded 2026-09-24
SoftCategoricalPdType maddpg_o/maddpg_local/trainer/maddpg.py ran no licence file found · pointer only · 9cf2b925ec95c7f2 · report fixture: signature flat:EagerTensor/2/float · returned SoftCategoricalPd · level recorded 2026-09-24
minimize_and_clip maddpg_o/maddpg_local/trainer/maddpg.py ran no licence file found · pointer only · 51c9fbcd079c6fda · report fixture: returned Operation · level recorded 2026-09-22
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
maddpg_o/maddpg_local/trainer/maddpg.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 61d3f2ae09e0df23 · report fixture: signature x:EagerTensor/2/float, axis:NoneType/0/? · returned EagerTensor · level recorded 2026-09-22
AgentTrainer maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · d0b7f852c271a2cb · report
BatchInput maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 410b8121d522d60d · report
BernoulliPd maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 7855bf32a05f6453 · report
BernoulliPdType maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 04989e6ce54eef99 · report
DiagGaussianPd maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 99ab37a0b854f64c · report
DiagGaussianPdType maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 9c5f519b1107c4a0 · report
MADDPGAgentTrainer maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · b2f7329c7900cbee · report
MultiDiscrete maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 19525957eb332eb2 · report
Pd maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 26b44f96043b4296 · report
PdType maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · a233d862ed1c5de8 · report
ReplayBuffer in 33 papers maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 0ec668ec81ebce4d · report
SoftCategoricalPd maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 1fe728fdf693afaf · report
SoftMultiCategoricalPd maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 9bb22eb75cfa28b6 · report
SoftMultiCategoricalPdType maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 8371d56181f23309 · report
TfInput maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 654b5868fdbabd66 · report
_Function maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 8523867a9c545bdf · report
absolute_scope_name maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 0f6bbf3f67ac6f9c · report
function in 6 papers maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 5b6a9e8f5134b90d · report
get_session maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 61c6759fad1b2459 · report
is_placeholder maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 7e5ebeb6de3d3d4a · report
make_pdtype maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 731751ece9e0b766 · report
make_update_exp maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 0d1a79fa849ba189 · report
max maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · cc0b8c4aa9b99165 · report
mean in 84 papers maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 8ebadf88476f8efe · report
p_train maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 79a21c888d914a27 · report
q_train maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · e03118d1752f94fe · report
scope_name maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 706116fa3e5a5a6c · report
scope_vars maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · de2061bedccd8dc9 · report
sum in 11 papers maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · fbab233112bf4d1e · report
var in 16 papers maddpg_o/maddpg_local/trainer/maddpg.py unverified no licence file found · pointer only · 598184a2689d36d0 · report
baradist/multiagent-particle-envs community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
ActorNetwork multiagent/ddpg/ddpg_agent.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 5d2b3c4f1fd1a9f4 · report fixture: returned ActorNetwork · level recorded 2026-09-22
CriticNetwork in 5 papers multiagent/ddpg/ddpg_agent.py ran · metamorphic tier: deterministic MIT (permissive) · 619856d2049bc612 · report fixture: returned CriticNetwork · level recorded 2026-09-22
OUActionNoise multiagent/ddpg/ddpg_agent.py ran MIT (permissive) · 1ea60fdd30545832 · report fixture: returned OUActionNoise · level recorded 2026-09-22
ReplayBuffer in 33 papers multiagent/ddpg/ddpg_agent.py ran MIT (permissive) · c90519f77627be1f · report fixture: returned ReplayBuffer · level recorded 2026-09-22
Agent in 42 papers multiagent/ddpg/ddpg_agent.py unverified MIT (permissive) · f3e14c78a36f2168 · report
biemann/Collaboration-and-Competition community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
DDPGAgent in 5 papers maddpg.py ran no licence file found · pointer only · bbf8b2fce98ed3c3 · report fixture: returned DDPGAgent · level recorded 2026-09-22
MADDPG maddpg.py ran no licence file found · pointer only · a3dd086ac1fbb639 · report fixture: signature state_all_agents:list/1/Tensor, noise:float/0/float · returned list · level recorded 2026-09-24
Network in 40 papers maddpg.py ran · metamorphic tier: deterministic no licence file found · pointer only · f6fceb14173df844 · report fixture: returned Network · level recorded 2026-09-22
OUNoise in 6 papers maddpg.py ran no licence file found · pointer only · 555ae48ebffc59d4 · report fixture: returned OUNoise · level recorded 2026-09-22
bonniesjli/MADDPG_Tennis_UnityML community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
Actor in 68 papers MADDPG.py ran fingerprinted no licence file found · pointer only · af7b2cc00bcf3971 · report fixture: returned Actor · level recorded 2026-09-22
Critic in 60 papers MADDPG.py ran no licence file found · pointer only · b89abb00e73f1560 · report fixture: returned Critic · level recorded 2026-09-22
ReplayBuffer in 33 papers MADDPG.py ran no licence file found · pointer only · 21d74b782714cf9e · report fixture: returned ReplayBuffer · level recorded 2026-09-22
Agent in 42 papers MADDPG.py unverified no licence file found · pointer only · c455aad4cf9e3d68 · report
MADDPG MADDPG.py unverified no licence file found · pointer only · b38b019a971f0e14 · report
cyanrain7/trpo-in-marl community (archive-listed) 1 sample, 0 ran · 1 unverified
HAPPO algorithms/happo_trainer.py unverified MIT (permissive) · 972d50b722edcc62 · report
isp1tze/MAProj community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Actor in 68 papers algo/maddpg/maddpg_agent.py ran fingerprinted no licence file found · pointer only · cbd481c5cf284628 · report fixture: returned Actor · level recorded 2026-09-22
Critic in 60 papers algo/maddpg/maddpg_agent.py ran no licence file found · pointer only · 0d8d2fce5fa8c834 · report fixture: returned Critic · level recorded 2026-09-22
MADDPG algo/maddpg/maddpg_agent.py ran no licence file found · pointer only · cc58450c6eb52f3a · report fixture: returned MADDPG · level recorded 2026-09-22
ReplayMemory in 11 papers algo/maddpg/maddpg_agent.py ran no licence file found · pointer only · 14185602fbb4fa11 · report fixture: returned ReplayMemory · level recorded 2026-09-22
soft_update in 8 papers algo/maddpg/maddpg_agent.py unverified no licence file found · pointer only · f0ba29ce2b116d79 · report
jingdic/rgmcomm community (archive-listed) 1 sample, 0 ran · 1 unverified
MADDPG RGMComm_stage1/maddpg/maddpg.py unverified no licence file found · pointer only · 00f4c151df8ceb67 · report
johannesharmse/multi_agent_RL community (archive-listed) 1 sample, 0 ran · 1 unverified
Critic in 60 papers ddpg.py unverified MIT (permissive) · e9875c7422df7fec · report
jyqhahah/rl_maddpg_matd3 community (archive-listed) 1 sample, 0 ran · 1 unverified
MADDPG algo/maddpg/maddpg_agent.py unverified no licence file found · pointer only · ba0b5facd7c2091a · report
krasing/DRLearningCollaboration community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Actor in 68 papers failed_collaborative/ddpg_agent_multi_2.py ran fingerprinted no licence file found · pointer only · ab8b87babe2b659e · report fixture: returned Actor · level recorded 2026-09-22
Critic in 60 papers failed_collaborative/ddpg_agent_multi_2.py ran no licence file found · pointer only · 9af882c88cb87dda · report fixture: returned Critic · level recorded 2026-09-22
OUNoise in 6 papers failed_collaborative/ddpg_agent_multi_2.py ran no licence file found · pointer only · a169b2555a871836 · report fixture: returned OUNoise · level recorded 2026-09-22
ReplayBuffer in 33 papers failed_collaborative/ddpg_agent_multi_2.py ran no licence file found · pointer only · 4cbc44a206f6120a · report fixture: returned ReplayBuffer · level recorded 2026-09-22
Agents failed_collaborative/ddpg_agent_multi_2.py unverified no licence file found · pointer only · ce87b1d927fb04e1 · report
ksajan/DDPG-MAPE community (archive-listed) 1 sample, 0 ran · 1 unverified
Actor in 68 papers multiagent-particle-envs/maddpg.py unverified no licence file found · pointer only · 85e19366b66e12c8 · report
mauricemager/multiagent-robot community (archive-listed) 2 samples, 0 ran · 2 unverified
DDPGAgent in 5 papers algorithms/maddpg.py unverified MIT (permissive) · 798b209df2b695ff · report
MADDPG algorithms/maddpg.py unverified MIT (permissive) · f02f8f35b7849439 · report
morning9393/HAPPO-HATRPO community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
HAPPO algorithms/happo_trainer.py ran MIT (permissive) · 14f32d9aecd1c394 · report fixture: returned HAPPO · level recorded 2026-09-22
PopArt algorithms/happo_trainer.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · cf971b9dc43b13b4 · report fixture: returned PopArt · level recorded 2026-09-22
check in 38 papers
census: 5 implementations from 6 papers, 4 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32
algorithms/happo_trainer.py ran · honoured contract MIT (permissive) · 9589eca5bae9de80 · report fixture: signature input:ndarray/2/float · returned Tensor · level recorded 2026-09-22
petsol/MultiAgentCooperation_UnityAgent_MADDPG_Udacity community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
Actor in 68 papers multiagent_resources.py ran fingerprinted no licence file found · pointer only · a17bd67f978b7355 · report fixture: returned Actor · level recorded 2026-09-22
Critic in 60 papers multiagent_resources.py ran no licence file found · pointer only · 6d943b1d04649de3 · report fixture: returned Critic · level recorded 2026-09-22
ExperienceBuffer multiagent_resources.py ran no licence file found · pointer only · b4481f38bbb906b5 · report fixture: returned ExperienceBuffer · level recorded 2026-09-22
OUActionNoise multiagent_resources.py ran no licence file found · pointer only · 458174da77a0b0ce · report fixture: returned OUActionNoise · level recorded 2026-09-22
Agent in 42 papers multiagent_resources.py unverified no licence file found · pointer only · a35198f4b2a98333 · report
philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
ActorNetwork maddpg.py ran fingerprinted no licence file found · pointer only · 19dd2e9c270f0dc6 · report fixture: returned ActorNetwork · level recorded 2026-09-22
Agent in 42 papers maddpg.py ran no licence file found · pointer only · 6e3b52a2c0014b70 · report fixture: returned Agent · level recorded 2026-09-22
CriticNetwork in 5 papers maddpg.py ran no licence file found · pointer only · 1a6507f0b27d66e3 · report fixture: returned CriticNetwork · level recorded 2026-09-22
MADDPG maddpg.py ran no licence file found · pointer only · af4f065d2ca09a90 · report fixture: returned MADDPG · level recorded 2026-09-22
pr-shukla/maddpg-keras community (archive-listed) 1 sample, 0 ran · 1 unverified
get_critic maddpg/model.py unverified MIT (permissive) · 3b0d740d86579224 · report
rainandwind1/MADDPG-reconstruct community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
Actor in 68 papers MADDPG/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 394e91b566a8e7eb · report fixture: returned Actor · level recorded 2026-09-22
Critic in 60 papers MADDPG/model.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 30449e98cba1cf61 · report fixture: returned Critic · level recorded 2026-09-22
Replaybuffer MADDPG/model.py ran MIT (permissive) · 74c1bafecdee5848 · report fixture: returned Replaybuffer · level recorded 2026-09-22
DDPG MADDPG/model.py unverified MIT (permissive) · a3a587bc7fe0ee77 · report
MADDPG MADDPG/model.py unverified MIT (permissive) · 9bc56ac4d586a2d2 · report
rainandwind1/Maddpg_multiagent community (archive-listed) 1 sample, 0 ran · 1 unverified
DDPG model.py unverified MIT (permissive) · a4bedfc0dceee998 · report
starry-sky6688/MADDPG community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
Actor in 68 papers maddpg/maddpg.py ran fingerprinted no licence file found · pointer only · b1b715fc5cea22be · report fixture: returned Actor · level recorded 2026-09-22
Critic in 60 papers maddpg/maddpg.py ran no licence file found · pointer only · 601cec5195b4709d · report fixture: returned Critic · level recorded 2026-09-22
MADDPG maddpg/maddpg.py unverified no licence file found · pointer only · eb82e9aa0da99b86 · report
thechrisyoon08/marl community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
Actor in 68 papers MADDPG/maddpg.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 19cc670e3070c844 · report fixture: signature obs:Tensor/2/float · returned Tensor · level recorded 2026-09-22
CentralizedCritic MADDPG/maddpg.py ran · metamorphic tier: invariant MIT (permissive) · 5809fd7ddfdc55c2 · report fixture: signature x:Tensor/2/float, a:Tensor/2/float · returned Tensor · level recorded 2026-09-22
DDPGAgent in 5 papers MADDPG/maddpg.py ran MIT (permissive) · 4471e9be4006d33f · report fixture: signature indiv_reward_batch:ndarray/1/float, indiv_obs_batch:ndarray/2/float, global_state_batch:ndarray/2/float, global_actions_batch:list/1/Tensor, global_next_state_batch:ndarray/2/float, next_global_actions:Tensor/2/float · returned NoneType · level recorded 2026-09-24
MADDPG MADDPG/maddpg.py unverified MIT (permissive) · 98101e244acd71e0 · report
MultiAgentReplayBuffer MADDPG/maddpg.py unverified MIT (permissive) · 053976ac8304e4a8 · report
xuehy/pytorch-maddpg community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
Critic in 60 papers MADDPG.py ran no licence file found · pointer only · a7f0fe3c4dffccc9 · report fixture: returned Critic · level recorded 2026-09-22
MADDPG MADDPG.py ran no licence file found · pointer only · bcbd9c4a35e9a9e0 · report fixture: returned MADDPG · level recorded 2026-09-22
ReplayMemory in 11 papers MADDPG.py ran no licence file found · pointer only · 535c542a4e41bb65 · report fixture: returned ReplayMemory · level recorded 2026-09-22
zowiezhang/stas community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Actor in 68 papers models/policy/COMA.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · d33580612fa8578d · report fixture: returned Actor · level recorded 2026-09-22
COMA models/policy/COMA.py ran no licence file found · pointer only · e6b6fc2b3a05ee48 · report fixture: returned COMA · level recorded 2026-09-22
Critic in 60 papers models/policy/COMA.py ran · metamorphic tier: deterministic no licence file found · pointer only · 6879c98b93ce7112 · report fixture: returned Critic · level recorded 2026-09-22
Memory in 19 papers models/policy/COMA.py ran no licence file found · pointer only · 51c877df80bace64 · report fixture: returned Memory · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
hidden_init in 7 papers repository not located ran · honoured contract licence of this copy not recorded · 24ee38e114b38bce · report fixture: signature layer:callable/0/? · returned tuple · level recorded 2026-09-22

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.

28 assemblies on this paper: 28 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

28 sibling assemblies for Multi-Agent Actor-Critic (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 28 sibling assemblies; the other 16 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 4 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 28 siblings

  1. COMA entry · level 1 · ran · e6b6fc2b3a05ee48
  2. Actor model · level 1 · ran · d33580612fa8578d
  3. Critic model · level 1 · ran · 6879c98b93ce7112
  4. Memory helper · level 1 · ran · 51c877df80bace64

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. Actor entry · level 0 · unverified · 85e19366b66e12c8

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 5 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) · 2 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 28 siblings

  1. MADDPG entry · level 0 · unverified · 9bc56ac4d586a2d2
  2. DDPG model · level 0 · unverified · a3a587bc7fe0ee77
  3. Actor model · level 1 · ran · 394e91b566a8e7eb
  4. Critic model · level 1 · ran · 30449e98cba1cf61
  5. Replaybuffer sampler · level 1 · ran · 74c1bafecdee5848

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 7 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. MADDPG entry · level 0 · unverified · 6551e7add10520be
  2. Agent helper · level 0 · unverified · 5d2d3b9ff319eb0d
  3. ReplayBuffer sampler · level 1 · ran · ae26aa48075ee6cb
  4. Actor model · level 1 · ran · 147d57177bbffdd9
  5. Critic model · level 1 · ran · 6c1f59af0972c70e
  6. OUNoise helper · level 1 · ran · db3bd13d21d6150c
  7. hidden_init helper · level 1 · ran · honoured contract · 24ee38e114b38bce

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 28 siblings

  1. Agent entry · level 0 · unverified · f3e14c78a36f2168
  2. ActorNetwork model · level 1 · ran · 5d2b3c4f1fd1a9f4
  3. CriticNetwork model · level 1 · ran · 619856d2049bc612
  4. OUActionNoise helper · level 1 · ran · 1ea60fdd30545832
  5. ReplayBuffer sampler · level 1 · ran · c90519f77627be1f

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 11 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. AttentionSAC entry · level 0 · unverified · 92865550d0fc369e
  2. AttentionAgent model · level 0 · unverified · 5e7a8abdf83466de
  3. AttentionCritic model · level 1 · ran · 23a16fcf13d93070
  4. disable_gradients helper · level 0 · unverified · 34bbc966346baa78
  5. enable_gradients helper · level 0 · unverified · 8e93ecfbcd3abb77
  6. hard_update helper · level 0 · unverified · e6250f15677e1203
  7. soft_update helper · level 0 · unverified · f36b207d39a0f07a
  8. DiscretePolicy model · level 1 · ran · b4fe457a99be3144
  9. BasePolicy model · level 1 · ran · e3579cc107de4c0a
  10. categorical_sample helper · level 1 · ran · our draft was wrong · 8a12d52820205fa8
  11. onehot_from_logits helper · level 1 · ran · our draft was wrong · 5290a0543b38c4dc

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 5 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. MADDPG entry · level 1 · ran · a3dd086ac1fbb639
  2. DDPGAgent helper · level 1 · ran · bbf8b2fce98ed3c3
  3. Network model · level 1 · ran · f6fceb14173df844
  4. OUNoise helper · level 1 · ran · 555ae48ebffc59d4
  5. hidden_init helper · level 1 · ran · honoured contract · 24ee38e114b38bce

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 3 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. HAPPO entry · level 1 · ran · 14f32d9aecd1c394
  2. PopArt helper · level 1 · ran · cf971b9dc43b13b4
  3. check helper · level 1 · ran · honoured contract · 9589eca5bae9de80

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 28 siblings

  1. MADDPG entry · level 0 · unverified · eb82e9aa0da99b86
  2. Actor model · level 1 · ran · b1b715fc5cea22be
  3. Critic model · level 1 · ran · 601cec5195b4709d

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 6 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. Agents entry · level 0 · unverified · ce87b1d927fb04e1
  2. Actor model · level 1 · ran · ab8b87babe2b659e
  3. Critic model · level 1 · ran · 9af882c88cb87dda
  4. OUNoise helper · level 1 · ran · a169b2555a871836
  5. ReplayBuffer sampler · level 1 · ran · 4cbc44a206f6120a
  6. hidden_init helper · level 1 · ran · honoured contract · 24ee38e114b38bce

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 28 siblings

  1. Agent entry · level 0 · unverified · a35198f4b2a98333
  2. Actor model · level 1 · ran · a17bd67f978b7355
  3. Critic model · level 1 · ran · 6d943b1d04649de3
  4. ExperienceBuffer sampler · level 1 · ran · b4481f38bbb906b5
  5. OUActionNoise helper · level 1 · ran · 458174da77a0b0ce

harvested Assembly for Multi-Agent Actor-Critic (graph method: Multi-Agent Actor-Critic). 18 bricks; individually on a fixture: 15 ran (of which 12 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 28 siblings

  1. HAPPO_Policy entry · level 0 · unverified · a78bf4c700ca5bb9
  2. Actor model · level 0 · unverified · fe0a30f4af252b51
  3. Critic model · level 0 · unverified · 598a59b21df91031
  4. ACTLayer helper · level 1 · ran · 788933ff608baaea
  5. CNNBase helper · level 1 · ran · 44f09ebd8f4371fa
  6. MLPBase helper · level 1 · ran · eb97113b662895e7
  7. RNNLayer helper · level 1 · ran · ff5a06e4902f81ab
  8. check helper · level 1 · ran · honoured contract · 4829105008c71d83
  9. init helper · level 1 · ran · our draft was wrong · 9de355e93051e4ad
  10. Bernoulli helper · level 1 · ran · ce4cd71349aedb12
  11. Categorical helper · level 1 · ran · 7e51bfa5785fa3e2
  12. DiagGaussian helper · level 1 · ran · 6072c4350e278037
  13. CNNLayer helper · level 1 · ran · 605e1876fb9959d1
  14. MLPLayer helper · level 1 · ran · 052cdd66a800bf26
  15. FixedBernoulli helper · level 1 · ran · a48b952a1d356122
  16. FixedCategorical helper · level 1 · ran · 16be22c531bda7dd
  17. FixedNormal helper · level 1 · ran · 2430b3c71fa829d4
  18. Flatten helper · level 1 · ran · dca1bdd65a0d90e0
  1. MADDPG · 9c15b02245652b8a · 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. MADDPG · a5801506ae9dbb86 · 5 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. MADDPG · acd0f0cb49555d04 · 7 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. MADDPG · b63df89ac823bf96 · 4 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. DDPG · cc6438be33b63b66 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. MADDPG · cd5c698f587b9e16 · 4 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) · 1 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 · assemblies[17] in the JSON twin
  7. MADDPGAgentTrainer · cfb588886b6d696e · 34 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 30 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. MADDPG · d2cdce2d3b6b4440 · 11 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. MADDPG · d8c5ad0642a476bd · 3 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. MADDPG · d9354f221d6787ec · 5 bricks; individually on a fixture: 3 ran (of which 0 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) · 2 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. MADDPG · e2975ac65ff9a792 · 5 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) · 2 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 · assemblies[22] in the JSON twin
  12. Actor · ebe5736503ac7fcc · 1 brick; individually on a fixture: 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 · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. get_critic · f2d3546c2874a360 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[24] in the JSON twin
  14. MADDPG · fb220d477eee1017 · 8 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[25] in the JSON twin
  15. MADDPG · fb700643b1f781f1 · 11 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[26] in the JSON twin
  16. Critic · fd2e13aaabe4f0d0 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[27] in the JSON twin

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="1706.02275") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Deep Reinforcement LearningMulti-agent Reinforcement LearningQ-LearningReinforcement LearningReinforcement Learning (RL)SMAC+reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
SMAC+ Def_Armored_sequential MADDPG Median Win Rate 90.6 #4 of 11 Archive leaderboard report
SMAC+ Def_Infantry_sequential MADDPG Median Win Rate 100 #1 of 11 Archive leaderboard report
SMAC+ Def_Outnumbered_sequential MADDPG Median Win Rate 81.3 #2 of 11 Archive leaderboard report
SMAC+ Off_Complicated_sequential MADDPG Median Win Rate 0.0 #4 of 4 Archive leaderboard report
SMAC+ Off_Distant_sequential MADDPG Median Win Rate 0.0 #4 of 4 Archive leaderboard report
SMAC+ Off_Hard_sequential MADDPG Median Win Rate 0.0 #3 of 4 Archive leaderboard report
SMAC+ Off_Near_sequential MADDPG Median Win Rate 75.0 #3 of 4 Archive leaderboard report
SMAC+ Off_Superhard_sequential MADDPG Median Win Rate 0.0 #4 of 4 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.

Methods

Introduced by this paper: MADDPG

AdamBatch NormalizationConvolutionDense ConnectionsExperience ReplayMADDPGQ-LearningReLUWeight Decay

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