Papers › Neural Architecture Search with Reinforcement Learning

Neural Architecture Search with Reinforcement Learning

5 Nov 2016arXiv:1611.01578archive 2025-07-28

Barret Zoph, Quoc V. Le

Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. On the CIFAR-10 dataset, our method, starting from scratch, can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy. Our CIFAR-10 model achieves a test error rate of 3.65, which is 0.09 percent better and 1.05x faster than the previous state-of-the-art model that used a similar architectural scheme. On the Penn Treebank dataset, our model can compose a novel recurrent cell that outperforms the widely-used LSTM cell, and other state-of-the-art baselines. Our cell achieves a test set perplexity of 62.4 on the Penn Treebank, which is 3.6 perplexity better than the previous state-of-the-art model. The cell can also be transferred to the character language modeling task on PTB and achieves a state-of-the-art perplexity of 1.214.

PaperPDFCodeCode Syntology ran

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

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

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

Code

No sample from the archive's official repository (tensorflow/models) is linked to this paper; the 5 samples below come from 2 community repositories. Syntology harvested code from tensorflow/models for 4 other papers.

tensorflow/models: Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method.

Syntology 5 code samples harvested from 2 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 5 samples from 2 repositories, 5 ran (3 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 6 of its repositories that Syntology harvested for other papers:

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

tensorflow/models officialmentioned in papertfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
GiuliaLanzillotta/INAS mentioned on GitHubpytorchMITSyntology: not harvested report
TreeLimes/QANAS mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
YaCpotato/B4ResearchDeepaugment mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improved Regularization of Convolutional Neural Networks with Cutout (arXiv:1708.04552; that paper's own run record: 21 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
YaCpotato/deepaugmentFix mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AutoAugment: Learning Augmentation Policies from Data (arXiv:1805.09501; that paper's own run record: 25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 2 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report
abcp4/DAPytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AutoAugment: Learning Augmentation Policies from Data (arXiv:1805.09501; that paper's own run record: 25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 2 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report
barisozmen/deepaugment mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improved Regularization of Convolutional Neural Networks with Cutout (arXiv:1708.04552; that paper's own run record: 21 ran (of which 3 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 3 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified) and AutoAugment: Learning Augmentation Policies from Data (arXiv:1805.09501; that paper's own run record: 25 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 1 honoured, 2 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 18 unverified); nothing checks that they implement this paper's method. report
carpedm20/ENAS-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
cshannonn/blackscholes_nas mentioned on GitHubSyntology: not harvested report
tally0818/NASNet mentioned on GitHubpytorchSyntology: not harvested report
titu1994/neural-architecture-search mentioned on GitHubtfSyntology: not harvested report
DataCanvasIO/Hypernets tfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MobileDets: Searching for Object Detection Architectures for Mobile Accelerators (arXiv:2004.14525; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

5 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 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
1ran · violated contract
2ran · our draft was wrong

Licence: 3 of the 5 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

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

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

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

TreeLimes/QANAS community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
get_data in 223 papers performance_prediction.py ran · our draft was wrong no licence file found · pointer only · 3ec9da1cd4329956 · report fixture: signature reader:reader/0/?, n:int/0/int, T:int/0/int · returned tuple · level recorded 2026-09-22
int_or_float in 5 papers performance_prediction.py ran · honoured contract no licence file found · pointer only · 75b2d837ccdfa9c0 · report fixture: signature s:str/0/str · returned int · level recorded 2026-09-22
permute_data in 6 papers performance_prediction.py ran · honoured contract fingerprinted no licence file found · pointer only · a20bae4c047fd876 · report fixture: signature x:ndarray/2/float, y:ndarray/1/int · returned tuple · level recorded 2026-09-22
carpedm20/ENAS-pytorch community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
add_argument_group in 31 papers config.py ran · our draft was wrong Apache-2.0 (permissive) · 6d80592fd6d47b2d · report fixture: signature name:str/0/str · returned _ArgumentGroup · level recorded 2026-09-22
str2bool in 533 papers config.py ran · violated contract Apache-2.0 (permissive) · e5b1aff86a339d0e · report fixture: signature v:str/0/str · returned bool · level recorded 2026-09-22

Tasks

Image ClassificationLanguage ModelingLanguage ModellingNatural Language UnderstandingNeural Architecture SearchReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification CIFAR-10 NAS-RL Percentage correct 96.4 #113 of 265 Archive leaderboard report
Language Modelling Penn Treebank (Character Level) NAS-RL Bit per Character (BPC) 1.214 #13 of 20 Archive leaderboard report
Language Modelling Penn Treebank (Character Level) NAS-RL Number of params 16.3M #13 of 20 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) NAS-RL Params 25M #32 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) NAS-RL Test perplexity 64.0 #32 of 43 Archive leaderboard report
Neural Architecture Search CIFAR-10 Image Classification NAS-RL-A + c/o Params 27.6M #10 of 19 Archive leaderboard report
Neural Architecture Search CIFAR-10 Image Classification NAS-RL-A + c/o Percentage error 2.4 #10 of 19 Archive leaderboard report

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

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