Papers › Playing Atari with Deep Reinforcement Learning

Playing Atari with Deep Reinforcement Learning

19 Dec 2013arXiv:1312.5602archive 2025-07-28

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.

PaperPDFCodeCode 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

Syntology 117 code samples harvested from 50 repositories linked to this paper: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified. Where Syntology's instrument failed: 16 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 117 samples from 50 repositories, 64 ran (46 with no instrument failure; 18 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 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

2023-MindSpore-1/ms-code-52 mentioned on GitHubmindsporeSyntology: not harvested report
AndrewJWashington/protodriver mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous Deep Q-Learning with Model-based Acceleration (arXiv:1603.00748; that paper's own run record: 2 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; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
Anshu1245/RL-CourseProject mentioned on GitHubSyntology: 1 sample, 0 ran · 1 unverified report
BH4/Deep-Reinforcement-Learning mentioned on GitHubSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
FauzaanQureshi/deep-Q-learning mentioned on GitHubSyntology: 1 sample, 0 ran · 1 unverified report
Gary-Shi/Tank mentioned on GitHubSyntology: not harvested report
InSpaceAI/RL-Zoo mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
Ishan-Kumar2/Reinforcement-Learning-on-2048 mentioned on GitHubSyntology: not harvested report
JackFurby/Breakout mentioned on GitHubtfGPL-3.0Syntology: not harvested report
JonasRSV/DQN mentioned on GitHubtfSyntology: not harvested report
JonasRSV/DQNTensorflow mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
JuliaPOMDP/DeepQLearning.jl mentioned on GitHubNOASSERTIONSyntology: not harvested report
K-tang-mkv/baseRLAlgorithm mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
KatyNTsachi/Hierarchical-RL mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dopamine: A Research Framework for Deep Reinforcement Learning (arXiv:1812.06110; that paper's own run record: 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) · 13 unverified); nothing checks that they implement this paper's method. report
KavindaKottege/DeepQ-Pong mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
Linging/Traffic-Signal-Control mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
LukasGardberg/cartpole mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
MOVzeroOne/DQN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Dueling Network Architectures for Deep Reinforcement Learning (arXiv:1511.06581; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
MateuszJanda/netris-ai-robot mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
R-Stefano/DQN mentioned on GitHubtfSyntology: not harvested report
RLeike/connect-four mentioned on GitHubjaxSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
Rabrg/dqn mentioned on GitHubpytorchSyntology: not harvested report
RandyDeng/gym_connect4 mentioned on GitHubGPL-3.0Syntology: not harvested report
RobotMobile/rl-paper-review mentioned on GitHubSyntology: not harvested report
SayhoKim/tetrisRL mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
Sheepsody/Batched-Impala-PyTorch mentioned on GitHubpytorchSyntology: 7 samples, 4 ran (1 instrument-failed) · 3 unverified report
ShivamShrirao/deep_Q_learning mentioned on GitHubSyntology: not harvested report
ShivamShrirao/deep_Q_learning_from_scratch mentioned on GitHubSyntology: not harvested report
TheFebrin/DeepRL-Pong mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
Wentworth1996/Summer_Intern_Progress mentioned on GitHubSyntology: not harvested report
alfredvc/paac mentioned on GitHubtfSyntology: 9 samples, 1 ran (1 instrument-failed) · 8 unverified report
avillemin/Minecraft-AI mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
behzaad/Deep_QLearning mentioned on GitHubnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
bjotho/Zelda1AI mentioned on GitHubSyntology: not harvested report
blakeMilner/DeepQLearning mentioned on GitHubtorchSyntology: not harvested report
borea17/efficient_rl mentioned on GitHubMITSyntology: not harvested report
borhanreo/Obstacle-Avoid-Car mentioned on GitHubMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
daviddcho/supermario mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
drforester/Q-learning-Intersection-Crossing mentioned on GitHubtfSyntology: not harvested report
dsgiitr/rl_2048 mentioned on GitHubtfSyntology: not harvested report
eddynelson/dqn mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
epignatelli/human-level-control-through-deep-reinforcement-learning mentioned on GitHubjaxApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
esmeralday/MARL mentioned on GitHubSyntology: not harvested report
eublefar/dqn mentioned on GitHubtfSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
filippogiruzzi/deep_q_learning mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
geeky-wizard/Atari-Deep-Reinforcement-Learning mentioned on GitHubSyntology: not harvested report
grass123-hub/DQN mentioned on GitHubmindsporeSyntology: not harvested report
harvitronix/reinforcement-learning-car mentioned on GitHubMITSyntology: not harvested report
igoracmorais/inteligencia_artificial mentioned on GitHubtfSyntology: not harvested report
invictos/InsacarDQN mentioned on GitHubtfSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
jonaths/dqn-grid mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
jonaths/tf-dqn mentioned on GitHubtfApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
joshiatul/game_playing mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Asynchronous Methods for Deep Reinforcement Learning (arXiv:1602.01783; that paper's own run record: 60 ran (of which 20 constructed an object rather than computing a result; 50 with no instrument failure: 2 honoured, 1 violated, 47 with no contract checked; 10 where Syntology's instrument failed) · 35 unverified); nothing checks that they implement this paper's method. report
kmdanielduan/DQN_Family_PyTorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
komejisatori/ReinforcementCar mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
kshitij-ingale/Reinforcement-Learning mentioned on GitHubtfSyntology: not harvested report
ktkachuk/Atari-with-Q-Learning mentioned on GitHubtfSyntology: not harvested report
markusdutschke/yahtzee mentioned on GitHubSyntology: not harvested report
marload/DeepRL-TensorFlow2 mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
marload/deep-rl-tf2 mentioned on GitHubtfApache-2.0Syntology: not harvested report
mfregeau/DeepLearning mentioned on GitHubSyntology: not harvested report
mindspore-courses/Deep-Reinforcement-Learning-Algorithms-with-MindSpore mentioned on GitHubmindsporeSyntology: not harvested report
nandomp/AICollaboratory mentioned on GitHubGPL-3.0Syntology: not harvested report
nathanin/pad mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
natsumeS/analysis mentioned on GitHubSyntology: not harvested report
near32/regym mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Reinforcement Learning with Double Q-learning (arXiv:1509.06461; that paper's own run record: 56 ran (of which 38 constructed an object rather than computing a result; 55 with no instrument failure: 0 honoured, 0 violated, 55 with no contract checked; 1 where Syntology's instrument failed) · 50 unverified) and Proximal Policy Optimization Algorithms (arXiv:1707.06347; that paper's own run record: 99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified); nothing checks that they implement this paper's method. report
niklasschmitz/DeepQLearning mentioned on GitHubjaxMITSyntology: not harvested report
ninja18/AtariDQN mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
omkarv/pong-from-pixels mentioned on GitHubMITSyntology: not harvested report
paintception/Deep-Quality-Value-Family mentioned on GitHubSyntology: not harvested report
paintception/Deep-Quality-Value-Family- mentioned on GitHubSyntology: not harvested report
parilo/rl-server mentioned on GitHubtfSyntology: 5 samples, 2 ran (2 instrument-failed) · 3 unverified report
pavitrakumar78/Playing-custom-games-using-Deep-Learning mentioned on GitHubSyntology: not harvested report
proroklab/popgym mentioned on GitHubpytorchSyntology: 14 samples, 7 ran (5 instrument-failed) · 7 unverified report
qiankun214/DQN-FlappyBird-python3 mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
rikluost/RL_DQN_Pong mentioned on GitHubtfSyntology: not harvested report
rishavb123/MineRL mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
saha0073/Deep-Reinforcement-Learning-to-play-Cartpole mentioned on GitHubtfSyntology: not harvested report
sourenaKhanzadeh/snakeAi mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
spragunr/deep_q_rl mentioned on GitHubBSD-3-ClauseSyntology: 1 sample, 0 ran · 1 unverified report
subhadip-maiti/tinydqn mentioned on GitHubtfApache-2.0Syntology: not harvested report
sunjeet95/Deep-Q-Network-using-Tensorflow mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
sygi/deep_q_rl mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
tcmxx/CNTKUnityTools mentioned on GitHubSyntology: not harvested report
tlohr/nfsu2-ai mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ugo-nama-kun/DQN-chainer mentioned on GitHubMITSyntology: not harvested report
vincentpalma/DQN-for-CaRL mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
vsquareg/RL_ERA mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
xValentim/Steering_Behaviors_with_pygame mentioned on GitHubtfSyntology: not harvested report
yaxinchen666/dce_pricingRL mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
Curt-Park/rainbow-is-all-you-need MITSyntology: not harvested report
DLR-RM/stable-baselines3 pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport (arXiv:2603.01771; that paper's own run record: 6 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
MaximeVandegar/Papers-in-100-Lines-of-Code pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
NervanaSystems/coach tfSyntology: not harvested report
OscarHuangWind/Preference-Guided-DQN-Atari pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
anita-hu/TF2-RL tfSyntology: 1 sample, 0 ran · 1 unverified report
bay3s/dqn pytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
chandar-lab/RLHive pytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
facebookresearch/rl jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark (arXiv:2306.17100; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
gordicaleksa/pytorch-learn-reinforcement-learning pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
han-won/PlayingAtariWithMindSpore mindsporeSyntology: not harvested report
hill-a/stable-baselines tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Reinforcement Learning with Double Q-learning (arXiv:1509.06461; that paper's own run record: 56 ran (of which 38 constructed an object rather than computing a result; 55 with no instrument failure: 0 honoured, 0 violated, 55 with no contract checked; 1 where Syntology's instrument failed) · 50 unverified) and Prioritized Experience Replay (arXiv:1511.05952; that paper's own run record: 80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified); nothing checks that they implement this paper's method. report
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
lvyufeng/DQN-MindSpore mindsporeMITSyntology: not harvested report
michaelnny/deep_rl_zoo pytorchSyntology: 5 samples, 3 ran (1 instrument-failed) · 2 unverified report
pytorch/rl jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Decision Transformer: Reinforcement Learning via Sequence Modeling (arXiv:2106.01345; that paper's own run record: 17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
ray-project/ray Syntology: not harvested report
tensorpack/tensorpack tfSyntology: 13 samples, 9 ran (4 instrument-failed) · 4 unverified report
toni-sm/skrl jaxMITSyntology: not harvested report
xiuyu0000/new_papers_codes mindsporeSyntology: not harvested report

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

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

Code Syntology ran Syntology

117 samples harvested: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 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.

5ran · honoured contract
16ran · our draft was wrong
2ran; the contract check could not run
41ran
53unverified

Licence: 56 of the 117 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 50 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”. For 4 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.

Anshu1245/RL-CourseProject community (archive-listed) 1 sample, 0 ran · 1 unverified
exp_replay DQN/dqn.py unverified no licence file found · pointer only · 8852f55a6471cb78 · report
BH4/Deep-Reinforcement-Learning community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
ExperienceReplay in 5 papers Training/qlearn.py ran MIT (permissive) · f9118b06dae7f603 · report fixture: returned ExperienceReplay · level recorded 2026-09-22
Training Training/qlearn.py ran MIT (permissive) · 54e74edb75cc6f83 · report fixture: returned Training · level recorded 2026-09-22
FauzaanQureshi/deep-Q-learning community (archive-listed) 1 sample, 0 ran · 1 unverified
CNN in 23 papers CNN.py unverified no licence file found · pointer only · ed92e17b3aae8048 · report
InSpaceAI/RL-Zoo community (archive-listed) 1 sample, 0 ran · 1 unverified
Model in 227 papers DQN.py unverified no licence file found · pointer only · 0f47d6422b2c5369 · report
JonasRSV/DQNTensorflow community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ExperienceReplay in 5 papers dqn.py ran · metamorphic tier: well formed fingerprinted no licence file found · pointer only · 96164b4731db1134 · report fixture: signature batchsz:int/0/int · returned tuple · level recorded 2026-09-22
DQN in 8 papers dqn.py unverified no licence file found · pointer only · 01a1660b174e9811 · report
K-tang-mkv/baseRLAlgorithm community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DQN in 8 papers algorithms/DQN_pytorch_offical/dqn.py ran · metamorphic tier: invariant no licence file found · pointer only · 7ac5ee56c6e889b6 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
KavindaKottege/DeepQ-Pong community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
huber_loss in 34 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket
DeepQ-Pong.py ran · honoured contract no licence file found · pointer only · eaf9a525f0459416 · report fixture: signature y:EagerTensor/2/float, q_value:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
atari_model DeepQ-Pong.py unverified no licence file found · pointer only · 21077a0a5bf80f4e · report
Linging/Traffic-Signal-Control community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
QNetwork in 11 papers Agent/networks.py ran no licence file found · pointer only · 391471b2e6f9888c · report fixture: returned QNetwork · level recorded 2026-09-22
QNetworkNIPS Agent/networks.py unverified no licence file found · pointer only · 7f1cd947395254b0 · report
LukasGardberg/cartpole community (archive-listed) 1 sample, 0 ran · 1 unverified
QAgent carpole_train.py unverified no licence file found · pointer only · 0e08e7a4d7c5d8b2 · report
MateuszJanda/netris-ai-robot community (archive-listed) 1 sample, 0 ran · 1 unverified
CachingAgent robot/agents/caching_agent.py unverified no licence file found · pointer only · 39be9974e39c4007 · report
RLeike/connect-four community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
zero_sum_loss agent.py ran · our draft was wrong no licence file found · pointer only · 1f72577dd8ccaa95 · report fixture: signature predict:callable/0/?, s1:ArrayImpl/2/float, a_:ArrayImpl/2/float, r_:ArrayImpl/2/float, s2:ArrayImpl/2/float, paras:dict/0/? · returned ArrayImpl · level recorded 2026-09-22
AbstractAgent in 5 papers agent.py unverified no licence file found · pointer only · 26d04828131d058e · report
FeedforwardAgent agent.py unverified no licence file found · pointer only · 82c4ff3ff8f63e05 · report
SayhoKim/tetrisRL community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DuelingDQN lib/models/ddqn.py ran no licence file found · pointer only · 8eceb653c628a651 · report fixture: returned DuelingDQN · level recorded 2026-09-22
Sheepsody/Batched-Impala-PyTorch community (archive-listed) 7 samples, 4 ran (1 instrument-failed) · 3 unverified
BaseBlock src/networks/ActorCritic.py ran · metamorphic tier: deterministic no licence file found · pointer only · 69b2f2e5a6967e4c · report fixture: returned BaseBlock · level recorded 2026-09-22
ResidualBlock in 100 papers src/networks/ActorCritic.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · cb2515fde4e1a0e0 · report fixture: returned ResidualBlock · level recorded 2026-09-22
ShallowConv src/networks/ActorCritic.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3298a4358c400287 · report fixture: returned ShallowConv · level recorded 2026-09-22
_output_size_conv2d src/networks/ActorCritic.py ran · our draft was wrong no licence file found · pointer only · 18e2a7b2917f4571 · report fixture: signature conv:callable/0/?, size:tuple/1/int · returned ndarray · level recorded 2026-09-22
ActorCriticLSTM src/networks/ActorCritic.py unverified no licence file found · pointer only · 9097edcc955ed803 · report
BodyType src/networks/ActorCritic.py unverified no licence file found · pointer only · d16973e80e747353 · report
DeepConv src/networks/ActorCritic.py unverified no licence file found · pointer only · 1e1c270d61b7ea4b · report
TheFebrin/DeepRL-Pong community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
DQN in 8 papers models/dqn_model.py ran MIT (permissive) · a54a3b810f63e7d1 · report fixture: returned DQN · level recorded 2026-09-22
IModel models/dqn_model.py ran · metamorphic tier: deterministic MIT (permissive) · 373f5c8eb72337f4 · report fixture: returned IModel · level recorded 2026-09-22
Model in 227 papers models/dqn_model.py ran · metamorphic tier: deterministic MIT (permissive) · 2e7175149cc42e4e · report fixture: returned Model · level recorded 2026-09-22
alfredvc/paac community (archive-listed) 9 samples, 1 ran (1 instrument-failed) · 8 unverified
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
networks.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 143311d10e7d046c · report fixture: signature _input:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
NatureNetwork networks.py unverified licence not identified · pointer only · dc3336e8f1fdf44a · report
Network in 40 papers networks.py unverified licence not identified · pointer only · e53b0eb94184ff85 · report
conv2d in 119 papers networks.py unverified licence not identified · pointer only · 4577713d4b86ef2b · report
conv_bias_variable networks.py unverified licence not identified · pointer only · 8e415301ac3c74a1 · report
conv_weight_variable networks.py unverified licence not identified · pointer only · 8d6b5d3084a9d52f · report
fc in 16 papers networks.py unverified licence not identified · pointer only · 11c5727aaabe378a · report
fc_bias_variable networks.py unverified licence not identified · pointer only · 77ef8402d44c461b · report
fc_weight_variable networks.py unverified licence not identified · pointer only · 4519c6fdfa92a307 · report
avillemin/Minecraft-AI community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Brain DQN/Agent.py ran · metamorphic tier: invariant no licence file found · pointer only · 8da78c4bfe306c3e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
borhanreo/Obstacle-Avoid-Car community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
movingaverage plotting.py ran fingerprinted MIT (permissive) · 215e80576955e5a8 · report fixture: signature y:ndarray/1/float, window_size:int/0/int · returned ndarray · level recorded 2026-09-26
params_to_filename learning.py ran MIT (permissive) · 3d3d55b5d8bd5963 · report fixture: signature params:dict/0/? · returned str · level recorded 2026-09-26
process_minibatch learning.py ran MIT (permissive) · 5448b18f64386fdb · report fixture: signature minibatch:list/1/tuple, model:callable/0/? · returned tuple · level recorded 2026-09-26
process_minibatch2 learning.py ran MIT (permissive) · 316b3c2ef7ed0d5e · report fixture: signature minibatch:list/1/tuple, model:callable/0/? · returned tuple · level recorded 2026-09-26
readable_output plotting.py ran MIT (permissive) · 8987d3556f2dbdbe · report fixture: signature filename:str/0/str · returned str · level recorded 2026-09-26
daviddcho/supermario community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DQN in 8 papers model.py ran no licence file found · pointer only · e65d2c13d9aa7641 · report fixture: returned DQN · level recorded 2026-09-22
eddynelson/dqn community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
build_q_network dqn/networks/dueling_network.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · d09a6a1f1807cb36 · report fixture: signature n_actions:int/0/int, input_shape:tuple/1/int, history_length:int/0/int · returned Functional · level recorded 2026-09-22
epignatelli/human-level-control-through-deep-reinforcement-learning community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
module dqn/base.py ran Apache-2.0 (permissive) · a8cd6ded600d9813 · report fixture: signature module_maker:callable/0/? · returned function · level recorded 2026-09-26
eublefar/dqn community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
map_dqn_var dqn.py ran · our draft was wrong no licence file found · pointer only · 1afb1d67cec9b38b · report fixture: signature var:MockVariable/0/?, to_iterable_vars:list/1/MockVariable, var_scope:str/0/str, iterable_scope:str/0/str · returned MockVariable · level recorded 2026-09-22
DQN in 8 papers dqn.py unverified no licence file found · pointer only · 5114ef5f140eab1f · report
filippogiruzzi/deep_q_learning community (archive-listed) 1 sample, 0 ran · 1 unverified
QEstimator dqn/models/estimators.py unverified no licence file found · pointer only · 42f3816a2d486c1a · report
invictos/InsacarDQN community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
customBoard agent/agent.py ran GPL-3.0 (copyleft) · pointer only · b93a2d0046d7cf64 · report fixture: returned customBoard · level recorded 2026-09-22
agent agent/agent.py unverified GPL-3.0 (copyleft) · pointer only · d2c233a4e64933cb · report
jonaths/dqn-grid community (archive-listed) 1 sample, 0 ran · 1 unverified
conv_network networks/qnetworks.py unverified Apache-2.0 (permissive) · 4f7455bb7e545246 · report
jonaths/tf-dqn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
sample_memories tiny_dqn.py ran fingerprinted Apache-2.0 (permissive) · df21990110979f81 · report fixture: signature batch_size:int/0/int · returned tuple · level recorded 2026-09-26
kmdanielduan/DQN_Family_PyTorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DQN_Conv networks.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9dc82f090fea3bda · report fixture: returned DQN_Conv · level recorded 2026-09-22
komejisatori/ReinforcementCar community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RLNetwork model/network.py ran · metamorphic tier: deterministic no licence file found · pointer only · 770e704a180ff720 · report fixture: returned RLNetwork · level recorded 2026-09-22
marload/DeepRL-TensorFlow2 community (archive-listed) 1 sample, 0 ran · 1 unverified
ActionStateModel DQN/DQN_Discrete.py unverified Apache-2.0 (permissive) · 623be0021af9cc32 · report
nathanin/pad community (archive-listed) 1 sample, 0 ran · 1 unverified
DuelingQ agent/models/duelingq.py unverified no licence file found · pointer only · 77ebfb9f870755e5 · report
ninja18/AtariDQN community (archive-listed) 1 sample, 0 ran · 1 unverified
atariAgent DQNModel.py unverified no licence file found · pointer only · e444b6d743c4c506 · report
parilo/rl-server community (archive-listed) 5 samples, 2 ran (2 instrument-failed) · 3 unverified
base_name tf_rl/conv_model.py ran · our draft was wrong no licence file found · pointer only · bff3b19f646bee04 · report fixture: signature var:MockVariable/0/? · returned str · level recorded 2026-09-22
base_name2 tf_rl/conv_model.py ran · our draft was wrong no licence file found · pointer only · dca827af2639f99d · report fixture: signature var:MockVariable/0/? · returned str · level recorded 2026-09-22
CNN in 23 papers tf_rl/conv_model.py unverified no licence file found · pointer only · 986b511bd19889fc · report
Layer in 20 papers tf_rl/conv_model.py unverified no licence file found · pointer only · 13f78b113956d77f · report
MLP in 375 papers tf_rl/conv_model.py unverified no licence file found · pointer only · 15169eebbda3dcc8 · report
proroklab/popgym community (archive-listed) 14 samples, 7 ran (5 instrument-failed) · 7 unverified
DropoutNd in 5 papers popgym/baselines/models/s4d.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · f67fec3bfe6045aa · report fixture: returned DropoutNd · level recorded 2026-09-22
LinearActivation in 16 papers popgym/baselines/models/s4d.py ran · our draft was wrong MIT (permissive) · 400c752a0d8d06f7 · report fixture: signature d_input:int/0/int, d_output:int/0/int, bias:bool/0/bool, transposed:bool/0/bool, activation:str/0/str, activate:bool/0/bool · returned Sequential · level recorded 2026-09-22
dplr in 7 papers popgym/baselines/models/s4d.py ran · our draft was wrong MIT (permissive) · 391c3adc43a9fb2d · report fixture: signature scaling:str/0/str, N:int/0/int, rank:int/0/int, H:int/0/int, dtype:dtype/0/?, real_scale:float/0/float, imag_scale:float/0/float, random_real:bool/0/bool, random_imag:bool/0/bool, normalize:bool/0/bool, diagonal:bool/0/bool, random_B:bool/0/bool · returned tuple · level recorded 2026-09-22
nplr in 6 papers popgym/baselines/models/s4d.py ran · our draft was wrong MIT (permissive) · 08037869b6206d12 · report fixture: signature measure:str/0/str, N:int/0/int, rank:int/0/int, dtype:dtype/0/?, diagonalize_precision:bool/0/bool · returned tuple · level recorded 2026-09-22
power in 16 papers popgym/baselines/models/s4d.py ran · our draft was wrong fingerprinted MIT (permissive) · 14bcfdbb8473e4b3 · report fixture: signature L:int/0/int, A:Tensor/2/float, v:Tensor/2/float · returned tuple · level recorded 2026-09-22
rank_correction in 7 papers popgym/baselines/models/s4d.py ran · honoured contract MIT (permissive) · 67e350096b3030fb · report fixture: signature measure:str/0/str, N:int/0/int, rank:int/0/int, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-22
transition in 16 papers popgym/baselines/models/s4d.py ran · our draft was wrong MIT (permissive) · d613b8ca99bc2295 · report fixture: signature measure:str/0/str, N:int/0/int · returned tuple · level recorded 2026-09-22
OptimModule in 5 papers popgym/baselines/models/s4d.py unverified MIT (permissive) · 30e46a646e08a7d8 · report
S4 popgym/baselines/models/s4d.py unverified MIT (permissive) · 58ded9af82892cc0 · report
SSKernel popgym/baselines/models/s4d.py unverified MIT (permissive) · 89b4b37f6d5d8c72 · report
SSKernelDiag popgym/baselines/models/s4d.py unverified MIT (permissive) · d78e88b5a6d2c2b1 · report
SSKernelNPLR popgym/baselines/models/s4d.py unverified MIT (permissive) · 6f34cfb42a2fac86 · report
combination in 8 papers popgym/baselines/models/s4d.py unverified MIT (permissive) · 4d830cd514f6cb32 · report
ssm in 8 papers popgym/baselines/models/s4d.py unverified MIT (permissive) · 284562b888d37de3 · report
qiankun214/DQN-FlappyBird-python3 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BrainDQN BrainDQN.py ran · metamorphic tier: deterministic no licence file found · pointer only · 81c2538f25d49bf5 · report fixture: returned BrainDQN · level recorded 2026-09-22
rishavb123/MineRL community (archive-listed) 1 sample, 0 ran · 1 unverified
make_model in 37 papers model.py unverified no licence file found · pointer only · 8f9da127eceb2a1d · report
sourenaKhanzadeh/snakeAi community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Linear_QNet model.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 6734b023c48264d1 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
spragunr/deep_q_rl community (archive-listed) 1 sample, 0 ran · 1 unverified
process_args in 17 papers deep_q_rl/launcher.py unverified BSD-3-Clause (permissive) · 57c6b35d80e952e1 · report
sunjeet95/Deep-Q-Network-using-Tensorflow community (archive-listed) 1 sample, 0 ran · 1 unverified
Network in 40 papers main_cartpole.py unverified no licence file found · pointer only · ee0b2a23c9478bfc · report
tlohr/nfsu2-ai community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
image_number CreateDataSet.py ran MIT (permissive) · 1e29c6e3df986421 · report fixture: signature image:str/0/str · returned int · level recorded 2026-09-26
vincentpalma/DQN-for-CaRL community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DQN in 8 papers dqn_training.py ran · metamorphic tier: invariant no licence file found · pointer only · c7a2e9b74e4de596 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
vsquareg/RL_ERA community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
neural_net nn.py ran; the contract check could not run (RAISES) MIT (permissive) · 634d6466b3771df7 · report fixture: signature num_sensors:int/0/int, params:list/1/int, load:str/0/str · returned Sequential · level recorded 2026-09-22
yaxinchen666/dce_pricingRL community (archive-listed) 1 sample, 0 ran · 1 unverified
DQNAgent dqn_s.py unverified no licence file found · pointer only · b80d6818598d15d7 · report
MaximeVandegar/Papers-in-100-Lines-of-Code community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DQN in 8 papers Playing_Atari_with_Deep_Reinforcement_Learning/dqn.py ran MIT (permissive) · cc31fb79a4c9cfad · report fixture: returned DQN · level recorded 2026-09-22
OscarHuangWind/Preference-Guided-DQN-Atari community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Net in 54 papers Network.py ran MIT (permissive) · 93b98bd6ec8a54eb · report fixture: returned Net · level recorded 2026-09-22
anita-hu/TF2-RL community (archive-listed) 1 sample, 0 ran · 1 unverified
DQN in 8 papers DQN/TF2_DQN_Basic.py unverified MIT (permissive) · 7a2a672d94b88c2c · report
bay3s/dqn community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
DQN in 8 papers src/agents/dqn.py ran no licence file found · pointer only · 9c1d06fe674d019d · report fixture: returned DQN · level recorded 2026-09-22
DQNBase src/agents/dqn.py unverified no licence file found · pointer only · f09be9cc319f8b95 · report
Replay src/agents/dqn.py unverified no licence file found · pointer only · 92a00d39074b7d60 · report
chandar-lab/RLHive community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
MLPNetwork in 6 papers hive/agents/qnets/atari/nature_atari_dqn.py ran MIT (permissive) · 7af2befd6fd71b28 · report fixture: returned MLPNetwork · level recorded 2026-09-22
NoisyLinear in 9 papers hive/agents/qnets/atari/nature_atari_dqn.py ran MIT (permissive) · e2d32d93aef8dd96 · report fixture: returned NoisyLinear · level recorded 2026-09-22
calculate_output_dim hive/agents/qnets/atari/nature_atari_dqn.py ran · honoured contract MIT (permissive) · 6ec20a43d727c364 · report fixture: signature net:callable/0/?, input_shape:int/0/int · returned Size · level recorded 2026-09-22
ConvNetwork hive/agents/qnets/atari/nature_atari_dqn.py unverified MIT (permissive) · c9bddbe2aee30eac · report
NatureAtariDQNModel hive/agents/qnets/atari/nature_atari_dqn.py unverified MIT (permissive) · 85acd99c58ce6d0c · report
gordicaleksa/pytorch-learn-reinforcement-learning community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DQN in 8 papers models/definitions/DQN.py ran MIT (permissive) · 51cf7eff17d1081c · report fixture: returned DQN · level recorded 2026-09-22
labmlai/annotated_deep_learning_paper_implementations community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Model in 227 papers labml_nn/rl/dqn/model.py ran MIT (permissive) · 0387692d5cb08179 · report fixture: signature obs:Tensor/4/float · returned Tensor · level recorded 2026-09-24
michaelnny/deep_rl_zoo community (archive-listed) 5 samples, 3 ran (1 instrument-failed) · 2 unverified
DqnConvNet deep_rl_zoo/networks/value.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 73b097a72c5ea2f5 · report fixture: signature x:Tensor/4/int · returned DqnNetworkOutputs · level recorded 2026-09-22
NatureCnnBackboneNet deep_rl_zoo/networks/value.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · c448520babac98f1 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
calc_conv2d_output deep_rl_zoo/networks/value.py ran · our draft was wrong Apache-2.0 (permissive) · 9c004a3c7f80a048 · report fixture: signature h_w:tuple/1/int, kernel_size:int/0/int, stride:int/0/int, pad:int/0/int, dilation:int/0/int · returned tuple · level recorded 2026-09-22
DqnNetworkOutputs deep_rl_zoo/networks/value.py unverified Apache-2.0 (permissive) · e7dc84f99d692574 · report
initialize_weights in 30 papers deep_rl_zoo/networks/value.py unverified Apache-2.0 (permissive) · 3f487113acd567b9 · report
tensorpack/tensorpack community (archive-listed) 13 samples, 9 ran (4 instrument-failed) · 4 unverified
LayerShapeLogger tensorpack/models/conv2d.py ran Apache-2.0 (permissive) · ddd25e3de70197a2 · report fixture: returned LayerShapeLogger · level recorded 2026-09-22
VariableHolder tensorpack/models/conv2d.py ran Apache-2.0 (permissive) · a1061c9f352373b7 · report fixture: returned VariableHolder · level recorded 2026-09-22
convert_to_tflayer_args tensorpack/models/conv2d.py ran · our draft was wrong Apache-2.0 (permissive) · 58a16fa9e75bc087 · report fixture: signature args_names:list/1/str, name_mapping:dict/0/? · returned function · level recorded 2026-09-22
get_data_format tensorpack/models/conv2d.py ran · our draft was wrong Apache-2.0 (permissive) · e57b423feb455f31 · report fixture: signature data_format:str/0/str, keras_mode:bool/0/bool · returned str · level recorded 2026-09-22
get_tf_version_tuple tensorpack/models/conv2d.py ran · metamorphic tier: well formed Apache-2.0 (permissive) · 436e0ec3f2b87eea · report fixture: returned tuple · level recorded 2026-09-22
layer_register tensorpack/models/conv2d.py ran · our draft was wrong Apache-2.0 (permissive) · 802a4fa23e5c7036 · report fixture: signature log_shape:bool/0/bool, use_scope:bool/0/bool · returned function · level recorded 2026-09-22
map_common_tfargs tensorpack/models/conv2d.py ran · our draft was wrong Apache-2.0 (permissive) · ac7dc76edd237aa9 · report fixture: signature kwargs:dict/0/? · returned dict · level recorded 2026-09-22
shape2d tensorpack/models/conv2d.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 8f8fae04132f94eb · report fixture: signature a:int/0/int · returned list · level recorded 2026-09-22
shape4d tensorpack/models/conv2d.py ran · honoured contract Apache-2.0 (permissive) · e97f3b4aab9510ab · report fixture: signature a:int/0/int, data_format:str/0/str · returned list · level recorded 2026-09-22
Conv2D in 10 papers tensorpack/models/conv2d.py unverified Apache-2.0 (permissive) · c1adecea275c4a2d · report
_register tensorpack/models/conv2d.py unverified Apache-2.0 (permissive) · 7a20c93d8aa9f48b · report
log_once tensorpack/models/conv2d.py unverified Apache-2.0 (permissive) · eecf538e06851adc · report
rename_get_variable tensorpack/models/conv2d.py unverified Apache-2.0 (permissive) · 00500c0bcb8ead09 · report

Method as code Syntology

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

44 assemblies on this paper: 44 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

44 sibling assemblies for deep learning model (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 44 sibling assemblies; the other 32 are listed with their counts; every brick is in this page's JSON twin.

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

one of 44 siblings

  1. agent entry · level 0 · unverified · d2c233a4e64933cb
  2. customBoard helper · level 1 · ran · b93a2d0046d7cf64

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

one of 44 siblings

  1. atari_model entry · level 0 · unverified · 21077a0a5bf80f4e
  2. huber_loss loss · level 1 · ran · honoured contract · eaf9a525f0459416

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

one of 44 siblings

  1. DQN_Conv entry · level 1 · ran · 9dc82f090fea3bda

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

one of 44 siblings

  1. DQN entry · level 1 · ran · 9c1d06fe674d019d
  2. DQNBase model · level 0 · unverified · f09be9cc319f8b95
  3. Replay sampler · level 0 · unverified · 92a00d39074b7d60

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

one of 44 siblings

  1. BrainDQN entry · level 1 · ran · 81c2538f25d49bf5

harvested Assembly for deep learning model (graph method: deep learning model). 8 bricks; individually on a fixture: 5 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; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 44 siblings

  1. ActorCriticLSTM entry · level 0 · unverified · 9097edcc955ed803
  2. BodyType helper · level 0 · unverified · d16973e80e747353
  3. DeepConv helper · level 0 · unverified · 1e1c270d61b7ea4b
  4. Flatten helper · level 1 · ran · e1419c05ef8cd25e
  5. ShallowConv helper · level 1 · ran · 3298a4358c400287
  6. BaseBlock helper · level 1 · ran · 69b2f2e5a6967e4c
  7. _output_size_conv2d helper · level 1 · ran · our draft was wrong · 18e2a7b2917f4571
  8. ResidualBlock helper · level 1 · ran · cb2515fde4e1a0e0

harvested Assembly for deep learning model (graph method: deep learning model). 13 bricks; individually on a fixture: 9 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 44 siblings

  1. Conv2D entry · level 0 · unverified · c1adecea275c4a2d
  2. VariableHolder helper · level 1 · ran · a1061c9f352373b7
  3. convert_to_tflayer_args helper · level 1 · ran · our draft was wrong · 58a16fa9e75bc087
  4. get_data_format helper · level 1 · ran · our draft was wrong · e57b423feb455f31
  5. get_tf_version_tuple helper · level 1 · ran · 436e0ec3f2b87eea
  6. layer_register helper · level 1 · ran · our draft was wrong · 802a4fa23e5c7036
  7. log_once helper · level 0 · unverified · eecf538e06851adc
  8. rename_get_variable helper · level 0 · unverified · 00500c0bcb8ead09
  9. shape2d helper · level 1 · ran · honoured contract · 8f8fae04132f94eb
  10. shape4d helper · level 1 · ran · honoured contract · e97f3b4aab9510ab
  11. map_common_tfargs helper · level 1 · ran · our draft was wrong · ac7dc76edd237aa9
  12. _register helper · level 0 · unverified · 7a20c93d8aa9f48b
  13. LayerShapeLogger helper · level 1 · ran · ddd25e3de70197a2

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

one of 44 siblings

  1. CachingAgent entry · level 0 · unverified · 39be9974e39c4007

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

one of 44 siblings

  1. Model entry · level 0 · unverified · 0f47d6422b2c5369

harvested Assembly for deep learning model (graph method: deep learning model). 16 bricks; individually on a fixture: 9 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

one of 44 siblings

  1. S4 entry · level 0 · unverified · 58ded9af82892cc0
  2. Activation helper · level 1 · ran · our draft was wrong · 89b10a8b26bbb7ed
  3. DropoutNd helper · level 1 · ran · f67fec3bfe6045aa
  4. LinearActivation helper · level 1 · ran · our draft was wrong · 400c752a0d8d06f7
  5. SSKernel helper · level 0 · unverified · 89b4b37f6d5d8c72
  6. SSKernelDiag model · level 0 · unverified · d78e88b5a6d2c2b1
  7. SSKernelNPLR model · level 0 · unverified · 6f34cfb42a2fac86
  8. combination helper · level 0 · unverified · 4d830cd514f6cb32
  9. power helper · level 1 · ran · our draft was wrong · 14bcfdbb8473e4b3
  10. OptimModule helper · level 0 · unverified · 30e46a646e08a7d8
  11. ssm helper · level 0 · unverified · 284562b888d37de3
  12. dplr helper · level 1 · ran · our draft was wrong · 391c3adc43a9fb2d
  13. nplr helper · level 1 · ran · our draft was wrong · 08037869b6206d12
  14. rank_correction helper · level 1 · ran · honoured contract · 67e350096b3030fb
  15. transition helper · level 1 · ran · our draft was wrong · d613b8ca99bc2295
  16. get_logger helper · level 1 · ran · our draft was wrong · 0fa25f334c0ad357

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

one of 44 siblings

  1. ActionStateModel entry · level 0 · unverified · 623be0021af9cc32

harvested Assembly for deep learning model (graph method: deep learning model). 9 bricks; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 44 siblings

  1. NatureNetwork entry · level 0 · unverified · dc3336e8f1fdf44a
  2. Network helper · level 0 · unverified · e53b0eb94184ff85
  3. conv2d model · level 0 · unverified · 4577713d4b86ef2b
  4. fc model · level 0 · unverified · 11c5727aaabe378a
  5. flatten data_transform · level 1 · ran · our draft was wrong · 143311d10e7d046c
  6. conv_bias_variable helper · level 0 · unverified · 8e415301ac3c74a1
  7. conv_weight_variable helper · level 0 · unverified · 8d6b5d3084a9d52f
  8. fc_bias_variable helper · level 0 · unverified · 77ef8402d44c461b
  9. fc_weight_variable helper · level 0 · unverified · 4519c6fdfa92a307
  1. DQN · 49a216250fd321f6 · 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. DuelingQ · 49c305507941b3b2 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. CNN · 4e72899547f22f4a · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. Model · 514461de3a43495c · 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[15] in the JSON twin
  5. exp_replay · 5785759aa1669ce4 · 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. Network · 59a8b8fb45adbb8c · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
  7. DQNAgent · 5b2d545580d3a128 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[18] in the JSON twin
  8. DQN · 62357ad4797bfcb2 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
  9. QEstimator · 684ec2e1a5e47cf2 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[20] in the JSON twin
  10. CNN · 6e57af12dd248fd3 · 5 bricks; individually on a fixture: 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) · 3 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
  11. QAgent · 795187741b72f1e7 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
  12. DQN · 7b357c3b81205a40 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
  13. DQN · 842dd39deaac4d11 · 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. QNetworkNIPS · 86cae09337d75849 · 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[25] in the JSON twin
  15. Net · 8ac0c9bdd1583b41 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[26] in the JSON twin
  16. FeedforwardAgent · 94f172f37baa92df · 3 bricks; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[27] in the JSON twin
  17. DuelingDQN · 97430635f330447d · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[28] in the JSON twin
  18. DQN · 9a14709b4dd44953 · 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result · The assembly has not been run end-to-end · assemblies[29] in the JSON twin
  19. neural_net · 9e2a56f8b76b3d00 · 1 brick; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[30] in the JSON twin
  20. build_q_network · a266ee242b5e1aae · 1 brick; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[31] in the JSON twin
  21. Training · ab055716f7c34d9a · 2 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) · 0 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[32] in the JSON twin
  22. atariAgent · ae69ef838e8a507b · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[33] in the JSON twin
  23. NatureAtariDQNModel · b2d2f047148a84bd · 5 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) · 2 unverified · The assembly has not been run end-to-end · assemblies[34] in the JSON twin
  24. DQN · b643ff6aa5c3a29e · 2 bricks; individually on a fixture: 1 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; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[35] in the JSON twin
  25. conv_network · ba0d58ab189da90d · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[36] in the JSON twin
  26. make_model · bcc83dbc875420ca · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[37] in the JSON twin
  27. DQN · c451c6a887e69c8a · 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[38] in the JSON twin
  28. Brain · d071bb5b24e6c044 · 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[39] in the JSON twin
  29. DQN · d2359c01365f36d7 · 2 bricks; 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[40] in the JSON twin
  30. DqnConvNet · d46b237c24ed8049 · 5 bricks; individually on a fixture: 3 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; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[41] in the JSON twin
  31. DQN · e879b171ae030117 · 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[42] in the JSON twin
  32. Linear_QNet · ec444becb9386bc4 · 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[43] 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="1312.5602") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Atari GamesDeep Reinforcement LearningMulti-Goal Reinforcement LearningQ-LearningReinforcement LearningReinforcement Learning (RL)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Beam Rider DQN Best Score 5184 #40 of 49 Archive leaderboard report
Atari Games Atari 2600 Breakout DQN Best Score 225 #46 of 58 Archive leaderboard report
Atari Games Atari 2600 Enduro DQN Best Score 661 #33 of 48 Archive leaderboard report
Atari Games Atari 2600 Pong DQN Best Score 21 #7 of 52 Archive leaderboard report
Atari Games Atari 2600 Q*Bert DQN Best Score 4500 #44 of 57 Archive leaderboard report
Atari Games Atari 2600 Seaquest DQN Best Score 1740 #42 of 57 Archive leaderboard report
Atari Games Atari 2600 Space Invaders DQN Best Score 1075 #45 of 55 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: DQN

ConvolutionDQNDense ConnectionsEpsilon Greedy ExplorationExperience ReplayQ-Learning

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