Papers › Playing Atari with Deep Reinforcement Learning
Playing Atari with Deep Reinforcement Learning
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.
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="1312.5602")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1312.5602", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1312.5602")
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:
- AndrewJWashington/protodriver, community (archive-listed): harvested for another paper, listed under the repository
- KatyNTsachi/Hierarchical-RL, community (archive-listed): harvested for another paper, listed under the repository
- MOVzeroOne/DQN, community (archive-listed): harvested for another paper, listed under the repository
- joshiatul/game_playing, community (archive-listed): harvested for another paper, listed under the repository
- near32/regym, community (archive-listed): harvested for 2 other papers, listed under the repository
- DLR-RM/stable-baselines3, community (archive-listed): harvested for another paper, listed under the repository
- facebookresearch/rl, community (archive-listed): harvested for another paper, listed under the repository
- hill-a/stable-baselines, community (archive-listed): harvested for 2 other papers, listed under the repository
- pytorch/rl, community (archive-listed): harvested for another paper, listed under the repository
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.
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.
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.
f9118b06dae7f603 · report
fixture: returned ExperienceReplay · level recorded 2026-09-22 54e74edb75cc6f83 · report
fixture: returned Training · level recorded 2026-09-22 0f47d6422b2c5369 · report
96164b4731db1134 · report
fixture: signature batchsz:int/0/int · returned tuple · level recorded 2026-09-22 7ac5ee56c6e889b6 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 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 21077a0a5bf80f4e · report
391471b2e6f9888c · report
fixture: returned QNetwork · level recorded 2026-09-22 7f1cd947395254b0 · report
39be9974e39c4007 · report
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 26d04828131d058e · report
82c4ff3ff8f63e05 · report
8eceb653c628a651 · report
fixture: returned DuelingDQN · level recorded 2026-09-22 69b2f2e5a6967e4c · report
fixture: returned BaseBlock · level recorded 2026-09-22 cb2515fde4e1a0e0 · report
fixture: returned ResidualBlock · level recorded 2026-09-22 3298a4358c400287 · report
fixture: returned ShallowConv · level recorded 2026-09-22 18e2a7b2917f4571 · report
fixture: signature conv:callable/0/?, size:tuple/1/int · returned ndarray · level recorded 2026-09-22 9097edcc955ed803 · report
d16973e80e747353 · report
1e1c270d61b7ea4b · report
a54a3b810f63e7d1 · report
fixture: returned DQN · level recorded 2026-09-22 373f5c8eb72337f4 · report
fixture: returned IModel · level recorded 2026-09-22 2e7175149cc42e4e · report
fixture: returned Model · level recorded 2026-09-22 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 dc3336e8f1fdf44a · report
e53b0eb94184ff85 · report
4577713d4b86ef2b · report
8e415301ac3c74a1 · report
8d6b5d3084a9d52f · report
11c5727aaabe378a · report
77ef8402d44c461b · report
4519c6fdfa92a307 · report
8da78c4bfe306c3e · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 215e80576955e5a8 · report
fixture: signature y:ndarray/1/float, window_size:int/0/int · returned ndarray · level recorded 2026-09-26 3d3d55b5d8bd5963 · report
fixture: signature params:dict/0/? · returned str · level recorded 2026-09-26 5448b18f64386fdb · report
fixture: signature minibatch:list/1/tuple, model:callable/0/? · returned tuple · level recorded 2026-09-26 316b3c2ef7ed0d5e · report
fixture: signature minibatch:list/1/tuple, model:callable/0/? · returned tuple · level recorded 2026-09-26 8987d3556f2dbdbe · report
fixture: signature filename:str/0/str · returned str · level recorded 2026-09-26 e65d2c13d9aa7641 · report
fixture: returned DQN · level recorded 2026-09-22 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 a8cd6ded600d9813 · report
fixture: signature module_maker:callable/0/? · returned function · level recorded 2026-09-26 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 42f3816a2d486c1a · report
b93a2d0046d7cf64 · report
fixture: returned customBoard · level recorded 2026-09-22 df21990110979f81 · report
fixture: signature batch_size:int/0/int · returned tuple · level recorded 2026-09-26 9dc82f090fea3bda · report
fixture: returned DQN_Conv · level recorded 2026-09-22 770e704a180ff720 · report
fixture: returned RLNetwork · level recorded 2026-09-22 77ebfb9f870755e5 · report
bff3b19f646bee04 · report
fixture: signature var:MockVariable/0/? · returned str · level recorded 2026-09-22 dca827af2639f99d · report
fixture: signature var:MockVariable/0/? · returned str · level recorded 2026-09-22 986b511bd19889fc · report
13f78b113956d77f · report
15169eebbda3dcc8 · report
f67fec3bfe6045aa · report
fixture: returned DropoutNd · level recorded 2026-09-22 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 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 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 14bcfdbb8473e4b3 · report
fixture: signature L:int/0/int, A:Tensor/2/float, v:Tensor/2/float · returned tuple · level recorded 2026-09-22 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 d613b8ca99bc2295 · report
fixture: signature measure:str/0/str, N:int/0/int · returned tuple · level recorded 2026-09-22 30e46a646e08a7d8 · report
4d830cd514f6cb32 · report
284562b888d37de3 · report
81c2538f25d49bf5 · report
fixture: returned BrainDQN · level recorded 2026-09-22 8f9da127eceb2a1d · report
6734b023c48264d1 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 57c6b35d80e952e1 · report
ee0b2a23c9478bfc · report
1e29c6e3df986421 · report
fixture: signature image:str/0/str · returned int · level recorded 2026-09-26 c7a2e9b74e4de596 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 634d6466b3771df7 · report
fixture: signature num_sensors:int/0/int, params:list/1/int, load:str/0/str · returned Sequential · level recorded 2026-09-22 cc31fb79a4c9cfad · report
fixture: returned DQN · level recorded 2026-09-22 93b98bd6ec8a54eb · report
fixture: returned Net · level recorded 2026-09-22 9c1d06fe674d019d · report
fixture: returned DQN · level recorded 2026-09-22 f09be9cc319f8b95 · report
92a00d39074b7d60 · report
7af2befd6fd71b28 · report
fixture: returned MLPNetwork · level recorded 2026-09-22 e2d32d93aef8dd96 · report
fixture: returned NoisyLinear · level recorded 2026-09-22 6ec20a43d727c364 · report
fixture: signature net:callable/0/?, input_shape:int/0/int · returned Size · level recorded 2026-09-22 c9bddbe2aee30eac · report
85acd99c58ce6d0c · report
51cf7eff17d1081c · report
fixture: returned DQN · level recorded 2026-09-22 0387692d5cb08179 · report
fixture: signature obs:Tensor/4/float · returned Tensor · level recorded 2026-09-24 73b097a72c5ea2f5 · report
fixture: signature x:Tensor/4/int · returned DqnNetworkOutputs · level recorded 2026-09-22 c448520babac98f1 · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22 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 e7dc84f99d692574 · report
3f487113acd567b9 · report
ddd25e3de70197a2 · report
fixture: returned LayerShapeLogger · level recorded 2026-09-22 a1061c9f352373b7 · report
fixture: returned VariableHolder · level recorded 2026-09-22 58a16fa9e75bc087 · report
fixture: signature args_names:list/1/str, name_mapping:dict/0/? · returned function · level recorded 2026-09-22 e57b423feb455f31 · report
fixture: signature data_format:str/0/str, keras_mode:bool/0/bool · returned str · level recorded 2026-09-22 436e0ec3f2b87eea · report
fixture: returned tuple · level recorded 2026-09-22 802a4fa23e5c7036 · report
fixture: signature log_shape:bool/0/bool, use_scope:bool/0/bool · returned function · level recorded 2026-09-22 ac7dc76edd237aa9 · report
fixture: signature kwargs:dict/0/? · returned dict · level recorded 2026-09-22 8f8fae04132f94eb · report
fixture: signature a:int/0/int · returned list · level recorded 2026-09-22 e97f3b4aab9510ab · report
fixture: signature a:int/0/int, data_format:str/0/str · returned list · level recorded 2026-09-22 c1adecea275c4a2d · report
7a20c93d8aa9f48b · report
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
- agent entry · level 0 · unverified ·
d2c233a4e64933cb - 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
- atari_model entry · level 0 · unverified ·
21077a0a5bf80f4e - 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
- 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
- DQN entry · level 1 · ran ·
9c1d06fe674d019d - DQNBase model · level 0 · unverified ·
f09be9cc319f8b95 - 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
- 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
- ActorCriticLSTM entry · level 0 · unverified ·
9097edcc955ed803 - BodyType helper · level 0 · unverified ·
d16973e80e747353 - DeepConv helper · level 0 · unverified ·
1e1c270d61b7ea4b - Flatten helper · level 1 · ran ·
e1419c05ef8cd25e - ShallowConv helper · level 1 · ran ·
3298a4358c400287 - BaseBlock helper · level 1 · ran ·
69b2f2e5a6967e4c - _output_size_conv2d helper · level 1 · ran · our draft was wrong ·
18e2a7b2917f4571 - 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
- Conv2D entry · level 0 · unverified ·
c1adecea275c4a2d - VariableHolder helper · level 1 · ran ·
a1061c9f352373b7 - convert_to_tflayer_args helper · level 1 · ran · our draft was wrong ·
58a16fa9e75bc087 - get_data_format helper · level 1 · ran · our draft was wrong ·
e57b423feb455f31 - get_tf_version_tuple helper · level 1 · ran ·
436e0ec3f2b87eea - layer_register helper · level 1 · ran · our draft was wrong ·
802a4fa23e5c7036 - log_once helper · level 0 · unverified ·
eecf538e06851adc - rename_get_variable helper · level 0 · unverified ·
00500c0bcb8ead09 - shape2d helper · level 1 · ran · honoured contract ·
8f8fae04132f94eb - shape4d helper · level 1 · ran · honoured contract ·
e97f3b4aab9510ab - map_common_tfargs helper · level 1 · ran · our draft was wrong ·
ac7dc76edd237aa9 - _register helper · level 0 · unverified ·
7a20c93d8aa9f48b - 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
- 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
- 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
- S4 entry · level 0 · unverified ·
58ded9af82892cc0 - Activation helper · level 1 · ran · our draft was wrong ·
89b10a8b26bbb7ed - DropoutNd helper · level 1 · ran ·
f67fec3bfe6045aa - LinearActivation helper · level 1 · ran · our draft was wrong ·
400c752a0d8d06f7 - SSKernel helper · level 0 · unverified ·
89b4b37f6d5d8c72 - SSKernelDiag model · level 0 · unverified ·
d78e88b5a6d2c2b1 - SSKernelNPLR model · level 0 · unverified ·
6f34cfb42a2fac86 - combination helper · level 0 · unverified ·
4d830cd514f6cb32 - power helper · level 1 · ran · our draft was wrong ·
14bcfdbb8473e4b3 - OptimModule helper · level 0 · unverified ·
30e46a646e08a7d8 - ssm helper · level 0 · unverified ·
284562b888d37de3 - dplr helper · level 1 · ran · our draft was wrong ·
391c3adc43a9fb2d - nplr helper · level 1 · ran · our draft was wrong ·
08037869b6206d12 - rank_correction helper · level 1 · ran · honoured contract ·
67e350096b3030fb - transition helper · level 1 · ran · our draft was wrong ·
d613b8ca99bc2295 - 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
- 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
- NatureNetwork entry · level 0 · unverified ·
dc3336e8f1fdf44a - Network helper · level 0 · unverified ·
e53b0eb94184ff85 - conv2d model · level 0 · unverified ·
4577713d4b86ef2b - fc model · level 0 · unverified ·
11c5727aaabe378a - flatten data_transform · level 1 · ran · our draft was wrong ·
143311d10e7d046c - conv_bias_variable helper · level 0 · unverified ·
8e415301ac3c74a1 - conv_weight_variable helper · level 0 · unverified ·
8d6b5d3084a9d52f - fc_bias_variable helper · level 0 · unverified ·
77ef8402d44c461b - fc_weight_variable helper · level 0 · unverified ·
4519c6fdfa92a307
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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