Papers › Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
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.
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):
get_harvested_code_for_paper(arxiv_id="1706.02275")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1706.02275", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1706.02275")
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:
- baicenxiao/shaping-advice, community (archive-listed): harvested for another paper, listed under the repository
- facebookresearch/benchmarl, community (archive-listed): harvested for another paper, listed under the repository
- madhur-tandon/RL-Project, community (archive-listed): harvested for another paper, listed under the repository
- quantumiracle/mars, community (archive-listed): harvested for another paper, listed under the repository
- semitable/multiagent-particle-envs, community (archive-listed): harvested for another paper, listed under the repository
- sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3, community (archive-listed): harvested for another paper, listed under the repository
- yannbouteiller/gym-airsimdroneracinglab, community (archive-listed): harvested for another paper, listed under the repository
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.
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.
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.
6c6569c6b5d38959 · report
e0a77db60f82cb02 · report
fixture: signature state:Tensor/2/float · returned Tensor · level recorded 2026-09-22 23a16fcf13d93070 · report
fixture: returned AttentionCritic · level recorded 2026-09-22 e3579cc107de4c0a · report
fixture: returned BasePolicy · level recorded 2026-09-22 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 8a12d52820205fa8 · report
fixture: signature probs:Tensor/2/float, use_cuda:bool/0/bool · returned tuple · level recorded 2026-09-22 5290a0543b38c4dc · report
fixture: signature logits:Tensor/2/float, eps:float/0/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22 5e7a8abdf83466de · report
92865550d0fc369e · report
34bbc966346baa78 · report
8e93ecfbcd3abb77 · report
e6250f15677e1203 · report
f36b207d39a0f07a · report
7153bd2279c31cfb · report
fixture: signature state:Tensor/2/float · returned Tensor · level recorded 2026-09-22 1e89d38fb0c5b84b · report
fixture: signature states:Tensor/2/float, actions:Tensor/2/float · returned Tensor · level recorded 2026-09-22 1b5ce00b5c4ba8e0 · report
0fe6e65cdf5950a9 · report
147d57177bbffdd9 · report
fixture: returned Actor · level recorded 2026-09-22 6c1f59af0972c70e · report
fixture: returned Critic · level recorded 2026-09-22 db3bd13d21d6150c · report
fixture: returned OUNoise · level recorded 2026-09-22 ae26aa48075ee6cb · report
fixture: returned ReplayBuffer · level recorded 2026-09-22 5d2d3b9ff319eb0d · report
d91c262ff01c1192 · report
fixture: signature X:Tensor/2/float · returned Tensor · level recorded 2026-09-22 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 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 f925a8c266bb2532 · report
fixture: signature logits:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22 43c7e814609746ee · report
fixture: signature shape:tuple/1/int, eps:float/0/float, tens_type:tensortype/0/float · returned Tensor · level recorded 2026-09-22 23ccb70277ce98c1 · report
a3e542c9d6910a27 · report
788933ff608baaea · report
fixture: returned ACTLayer · level recorded 2026-09-22 ce4cd71349aedb12 · report
fixture: returned Bernoulli · level recorded 2026-09-22 6072c4350e278037 · report
fixture: returned DiagGaussian · level recorded 2026-09-22 a48b952a1d356122 · report
fixture: returned FixedBernoulli · level recorded 2026-09-22 2430b3c71fa829d4 · report
fixture: returned FixedNormal · level recorded 2026-09-22 eb97113b662895e7 · report
fixture: returned MLPBase · level recorded 2026-09-22 052cdd66a800bf26 · report
fixture: returned MLPLayer · level recorded 2026-09-22 ff5a06e4902f81ab · report
fixture: returned RNNLayer · level recorded 2026-09-22 fe0a30f4af252b51 · report
598a59b21df91031 · report
bab2a198c923111d · report
fixture: signature data:Tensor/2/float · returned dict · level recorded 2026-09-24 9cf2b925ec95c7f2 · report
fixture: signature flat:EagerTensor/2/float · returned SoftCategoricalPd · level recorded 2026-09-24 51c9fbcd079c6fda · report
fixture: returned Operation · level recorded 2026-09-22 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 d0b7f852c271a2cb · report
410b8121d522d60d · report
7855bf32a05f6453 · report
04989e6ce54eef99 · report
99ab37a0b854f64c · report
9c5f519b1107c4a0 · report
b2f7329c7900cbee · report
19525957eb332eb2 · report
26b44f96043b4296 · report
a233d862ed1c5de8 · report
0ec668ec81ebce4d · report
1fe728fdf693afaf · report
9bb22eb75cfa28b6 · report
8371d56181f23309 · report
654b5868fdbabd66 · report
8523867a9c545bdf · report
0f6bbf3f67ac6f9c · report
5b6a9e8f5134b90d · report
61c6759fad1b2459 · report
7e5ebeb6de3d3d4a · report
731751ece9e0b766 · report
0d1a79fa849ba189 · report
cc0b8c4aa9b99165 · report
8ebadf88476f8efe · report
79a21c888d914a27 · report
e03118d1752f94fe · report
706116fa3e5a5a6c · report
de2061bedccd8dc9 · report
fbab233112bf4d1e · report
598184a2689d36d0 · report
5d2b3c4f1fd1a9f4 · report
fixture: returned ActorNetwork · level recorded 2026-09-22 619856d2049bc612 · report
fixture: returned CriticNetwork · level recorded 2026-09-22 1ea60fdd30545832 · report
fixture: returned OUActionNoise · level recorded 2026-09-22 c90519f77627be1f · report
fixture: returned ReplayBuffer · level recorded 2026-09-22 f3e14c78a36f2168 · report
bbf8b2fce98ed3c3 · report
fixture: returned DDPGAgent · level recorded 2026-09-22 a3dd086ac1fbb639 · report
fixture: signature state_all_agents:list/1/Tensor, noise:float/0/float · returned list · level recorded 2026-09-24 f6fceb14173df844 · report
fixture: returned Network · level recorded 2026-09-22 555ae48ebffc59d4 · report
fixture: returned OUNoise · level recorded 2026-09-22 af7b2cc00bcf3971 · report
fixture: returned Actor · level recorded 2026-09-22 b89abb00e73f1560 · report
fixture: returned Critic · level recorded 2026-09-22 21d74b782714cf9e · report
fixture: returned ReplayBuffer · level recorded 2026-09-22 c455aad4cf9e3d68 · report
cbd481c5cf284628 · report
fixture: returned Actor · level recorded 2026-09-22 0d8d2fce5fa8c834 · report
fixture: returned Critic · level recorded 2026-09-22 cc58450c6eb52f3a · report
fixture: returned MADDPG · level recorded 2026-09-22 14185602fbb4fa11 · report
fixture: returned ReplayMemory · level recorded 2026-09-22 f0ba29ce2b116d79 · report
00f4c151df8ceb67 · report
ba0b5facd7c2091a · report
ab8b87babe2b659e · report
fixture: returned Actor · level recorded 2026-09-22 9af882c88cb87dda · report
fixture: returned Critic · level recorded 2026-09-22 a169b2555a871836 · report
fixture: returned OUNoise · level recorded 2026-09-22 4cbc44a206f6120a · report
fixture: returned ReplayBuffer · level recorded 2026-09-22 ce87b1d927fb04e1 · report
85e19366b66e12c8 · report
14f32d9aecd1c394 · report
fixture: returned HAPPO · level recorded 2026-09-22 cf971b9dc43b13b4 · report
fixture: returned PopArt · level recorded 2026-09-22 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 a17bd67f978b7355 · report
fixture: returned Actor · level recorded 2026-09-22 6d943b1d04649de3 · report
fixture: returned Critic · level recorded 2026-09-22 b4481f38bbb906b5 · report
fixture: returned ExperienceBuffer · level recorded 2026-09-22 458174da77a0b0ce · report
fixture: returned OUActionNoise · level recorded 2026-09-22 a35198f4b2a98333 · report
19dd2e9c270f0dc6 · report
fixture: returned ActorNetwork · level recorded 2026-09-22 6e3b52a2c0014b70 · report
fixture: returned Agent · level recorded 2026-09-22 1a6507f0b27d66e3 · report
fixture: returned CriticNetwork · level recorded 2026-09-22 af4f065d2ca09a90 · report
fixture: returned MADDPG · level recorded 2026-09-22 394e91b566a8e7eb · report
fixture: returned Actor · level recorded 2026-09-22 30449e98cba1cf61 · report
fixture: returned Critic · level recorded 2026-09-22 74c1bafecdee5848 · report
fixture: returned Replaybuffer · level recorded 2026-09-22 b1b715fc5cea22be · report
fixture: returned Actor · level recorded 2026-09-22 601cec5195b4709d · report
fixture: returned Critic · level recorded 2026-09-22 19cc670e3070c844 · report
fixture: signature obs:Tensor/2/float · returned Tensor · level recorded 2026-09-22 5809fd7ddfdc55c2 · report
fixture: signature x:Tensor/2/float, a:Tensor/2/float · returned Tensor · level recorded 2026-09-22 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 a7f0fe3c4dffccc9 · report
fixture: returned Critic · level recorded 2026-09-22 bcbd9c4a35e9a9e0 · report
fixture: returned MADDPG · level recorded 2026-09-22 535c542a4e41bb65 · report
fixture: returned ReplayMemory · level recorded 2026-09-22 d33580612fa8578d · report
fixture: returned Actor · level recorded 2026-09-22 e6b6fc2b3a05ee48 · report
fixture: returned COMA · level recorded 2026-09-22 6879c98b93ce7112 · report
fixture: returned Critic · level recorded 2026-09-22 51c877df80bace64 · report
fixture: returned Memory · level recorded 2026-09-22 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.
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
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
- 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
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
- MADDPG entry · level 0 · unverified ·
6551e7add10520be - Agent helper · level 0 · unverified ·
5d2d3b9ff319eb0d - ReplayBuffer sampler · level 1 · ran ·
ae26aa48075ee6cb - Actor model · level 1 · ran ·
147d57177bbffdd9 - Critic model · level 1 · ran ·
6c1f59af0972c70e - OUNoise helper · level 1 · ran ·
db3bd13d21d6150c - 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
- Agent entry · level 0 · unverified ·
f3e14c78a36f2168 - ActorNetwork model · level 1 · ran ·
5d2b3c4f1fd1a9f4 - CriticNetwork model · level 1 · ran ·
619856d2049bc612 - OUActionNoise helper · level 1 · ran ·
1ea60fdd30545832 - 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
- AttentionSAC entry · level 0 · unverified ·
92865550d0fc369e - AttentionAgent model · level 0 · unverified ·
5e7a8abdf83466de - AttentionCritic model · level 1 · ran ·
23a16fcf13d93070 - disable_gradients helper · level 0 · unverified ·
34bbc966346baa78 - enable_gradients helper · level 0 · unverified ·
8e93ecfbcd3abb77 - hard_update helper · level 0 · unverified ·
e6250f15677e1203 - soft_update helper · level 0 · unverified ·
f36b207d39a0f07a - DiscretePolicy model · level 1 · ran ·
b4fe457a99be3144 - BasePolicy model · level 1 · ran ·
e3579cc107de4c0a - categorical_sample helper · level 1 · ran · our draft was wrong ·
8a12d52820205fa8 - 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
- MADDPG entry · level 1 · ran ·
a3dd086ac1fbb639 - DDPGAgent helper · level 1 · ran ·
bbf8b2fce98ed3c3 - Network model · level 1 · ran ·
f6fceb14173df844 - OUNoise helper · level 1 · ran ·
555ae48ebffc59d4 - 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
- HAPPO entry · level 1 · ran ·
14f32d9aecd1c394 - PopArt helper · level 1 · ran ·
cf971b9dc43b13b4 - 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
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
- Agents entry · level 0 · unverified ·
ce87b1d927fb04e1 - Actor model · level 1 · ran ·
ab8b87babe2b659e - Critic model · level 1 · ran ·
9af882c88cb87dda - OUNoise helper · level 1 · ran ·
a169b2555a871836 - ReplayBuffer sampler · level 1 · ran ·
4cbc44a206f6120a - 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
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
- HAPPO_Policy entry · level 0 · unverified ·
a78bf4c700ca5bb9 - Actor model · level 0 · unverified ·
fe0a30f4af252b51 - Critic model · level 0 · unverified ·
598a59b21df91031 - ACTLayer helper · level 1 · ran ·
788933ff608baaea - CNNBase helper · level 1 · ran ·
44f09ebd8f4371fa - MLPBase helper · level 1 · ran ·
eb97113b662895e7 - RNNLayer helper · level 1 · ran ·
ff5a06e4902f81ab - check helper · level 1 · ran · honoured contract ·
4829105008c71d83 - init helper · level 1 · ran · our draft was wrong ·
9de355e93051e4ad - Bernoulli helper · level 1 · ran ·
ce4cd71349aedb12 - Categorical helper · level 1 · ran ·
7e51bfa5785fa3e2 - DiagGaussian helper · level 1 · ran ·
6072c4350e278037 - CNNLayer helper · level 1 · ran ·
605e1876fb9959d1 - MLPLayer helper · level 1 · ran ·
052cdd66a800bf26 - FixedBernoulli helper · level 1 · ran ·
a48b952a1d356122 - FixedCategorical helper · level 1 · ran ·
16be22c531bda7dd - FixedNormal helper · level 1 · ran ·
2430b3c71fa829d4 - Flatten helper · level 1 · ran ·
dca1bdd65a0d90e0
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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