Papers › Noisy Networks for Exploration

Noisy Networks for Exploration

30 Jun 2017ICLR 2018 1arXiv:1706.10295archive 2025-07-28

Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Remi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg

We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration. The parameters of the noise are learned with gradient descent along with the remaining network weights. NoisyNet is straightforward to implement and adds little computational overhead. We find that replacing the conventional exploration heuristics for A3C, DQN and dueling agents (entropy reward and ϵ-greedy respectively) with NoisyNet yields substantially higher scores for a wide range of Atari games, in some cases advancing the agent from sub to super-human performance.

PaperPDFConference PDFCodeCode Syntology ran

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

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

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

Code

Syntology 3 code samples harvested from 2 repositories linked to this paper: 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. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: community (archive-listed): 3 samples from 2 repositories, 1 ran (0 with no instrument failure; 1 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 5 of its repositories that Syntology harvested for other papers:

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

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

BY571/DQN-Atari-Agents mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
Curt-Park/rainbow-is-all-you-need mentioned on GitHubMITSyntology: not harvested report
Kaixhin/NoisyNet-A3C mentioned on GitHubpytorchSyntology: 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
LilTwo/DRL-using-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
MOVzeroOne/DQN mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
YanSong97/Master-thesis mentioned on GitHubpytorchSyntology: not harvested report
behzadanksu/rl-attack mentioned on GitHubtfSyntology: not harvested report
behzadanksu/rlattack-dev mentioned on GitHubtfSyntology: not harvested report
chainer/chainerrl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ChainerRL: A Deep Reinforcement Learning Library (arXiv:1912.03905; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
hw9603/DQfD-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
mindspore-courses/Rainbow-MindSpore mentioned on GitHubmindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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
seungjaeryanlee/rldb mentioned on GitHubSyntology: not harvested report
thomashirtz/noisy-networks mentioned on GitHubpytorchSyntology: not harvested report
chandar-lab/RLHive pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 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) 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
opendilab/DI-engine pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Hindsight Experience Replay (arXiv:1707.01495; that paper's own run record: 16 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified), Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified), 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) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report

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

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

Code Syntology ran Syntology

3 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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.

1ran; the contract check could not run
2unverified

Licence: 3 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

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

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

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

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

BY571/DQN-Atari-Agents community (archive-listed) 1 sample, 0 ran · 1 unverified
run in 143 papers run_atari_dqn.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 34182f569fae27fe · report
MOVzeroOne/DQN community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
observation_converter src/run_model.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) licence of this copy not recorded · 833c1425c5723274 · report fixture: returned Tensor · level recorded 2026-09-22
choose_action in 6 papers src/run_model.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 2bd713d31dc46902 · report

Tasks

Atari GamesDeep Reinforcement LearningEfficient ExplorationReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Alien NoisyNet-Dueling Score 5778 #15 of 49 Archive leaderboard report
Atari Games Atari 2600 Amidar NoisyNet-Dueling Score 3537 #5 of 48 Archive leaderboard report
Atari Games Atari 2600 Assault NoisyNet-Dueling Score 11231 #16 of 45 Archive leaderboard report
Atari Games Atari 2600 Asterix NoisyNet-Dueling Score 28350 #22 of 49 Archive leaderboard report
Atari Games Atari 2600 Asteroids NoisyNet-Dueling Score 86700 #10 of 43 Archive leaderboard report
Atari Games Atari 2600 Atlantis NoisyNet-Dueling Score 972175 #14 of 42 Archive leaderboard report
Atari Games Atari 2600 Bank Heist NoisyNet-Dueling Score 1318 #11 of 45 Archive leaderboard report
Atari Games Atari 2600 Battle Zone NoisyNet-Dueling Score 52262 #12 of 47 Archive leaderboard report
Atari Games Atari 2600 Beam Rider NoisyNet-Dueling Score 23134 #19 of 49 Archive leaderboard report
Atari Games Atari 2600 Berzerk NoisyNet-Dueling Score 1896 #17 of 39 Archive leaderboard report
Atari Games Atari 2600 Boxing NoisyNet-Dueling Score 100 #3 of 45 Archive leaderboard report
Atari Games Atari 2600 Breakout NoisyNet-Dueling Score 263 #45 of 58 Archive leaderboard report
Atari Games Atari 2600 Centipede NoisyNet-Dueling Score 7596 #24 of 45 Archive leaderboard report
Atari Games Atari 2600 Chopper Command NoisyNet-Dueling Score 11477 #18 of 45 Archive leaderboard report
Atari Games Atari 2600 Crazy Climber NoisyNet-Dueling Score 171171 #12 of 49 Archive leaderboard report
Atari Games Atari 2600 Defender NoisyNet-Dueling Score 42253 #15 of 21 Archive leaderboard report
Atari Games Atari 2600 Demon Attack NoisyNet-Dueling Score 69311 #27 of 46 Archive leaderboard report
Atari Games Atari 2600 Double Dunk NoisyNet-Dueling Score 1 #20 of 43 Archive leaderboard report
Atari Games Atari 2600 Enduro NoisyNet-Dueling Score 2013 #20 of 48 Archive leaderboard report
Atari Games Atari 2600 Fishing Derby NoisyNet-Dueling Score 57 #10 of 44 Archive leaderboard report
Atari Games Atari 2600 Freeway NoisyNet-Dueling Score 34 #3 of 59 Archive leaderboard report
Atari Games Atari 2600 Frostbite NoisyNet-Dueling Score 2923 #26 of 53 Archive leaderboard report
Atari Games Atari 2600 Gopher NoisyNet-Dueling Score 38909 #17 of 43 Archive leaderboard report
Atari Games Atari 2600 Gravitar NoisyNet-Dueling Score 2209 #16 of 53 Archive leaderboard report
Atari Games Atari 2600 HERO NoisyNet-Dueling Score 31533 #13 of 44 Archive leaderboard report
Atari Games Atari 2600 Ice Hockey NoisyNet-Dueling Score 3 #15 of 43 Archive leaderboard report
Atari Games Atari 2600 Kangaroo NoisyNet-Dueling Score 15227 #6 of 47 Archive leaderboard report
Atari Games Atari 2600 Krull NoisyNet-Dueling Score 10754 #14 of 45 Archive leaderboard report
Atari Games Atari 2600 Kung-Fu Master NoisyNet-Dueling Score 41672 #20 of 43 Archive leaderboard report
Atari Games Atari 2600 Montezuma's Revenge NoisyNet-Dueling Score 57 #31 of 50 Archive leaderboard report
Atari Games Atari 2600 Ms. Pacman NoisyNet-Dueling Score 5546 #19 of 47 Archive leaderboard report
Atari Games Atari 2600 Name This Game NoisyNet-Dueling Score 12211 #22 of 43 Archive leaderboard report
Atari Games Atari 2600 Phoenix NoisyNet-Dueling Score 10379 #19 of 21 Archive leaderboard report
Atari Games Atari 2600 Pitfall! NoisyNet-Dueling Score 0 #8 of 23 Archive leaderboard report
Atari Games Atari 2600 Pong NoisyNet-Dueling Score 21 #6 of 52 Archive leaderboard report
Atari Games Atari 2600 Private Eye NoisyNet-Dueling Score 279 #31 of 52 Archive leaderboard report
Atari Games Atari 2600 Q*Bert NoisyNet-Dueling Score 27121 #15 of 57 Archive leaderboard report
Atari Games Atari 2600 Road Runner NoisyNet-Dueling Score 234352 #8 of 44 Archive leaderboard report
Atari Games Atari 2600 Robotank NoisyNet-Dueling Score 64 #18 of 42 Archive leaderboard report
Atari Games Atari 2600 Seaquest NoisyNet-Dueling Score 16754 #17 of 57 Archive leaderboard report
Atari Games Atari 2600 Skiing NoisyNet-Dueling Score -7550 #8 of 23 Archive leaderboard report
Atari Games Atari 2600 Solaris NoisyNet-Dueling Score 6522 #12 of 23 Archive leaderboard report
Atari Games Atari 2600 Space Invaders NoisyNet-Dueling Score 5909 #21 of 55 Archive leaderboard report
Atari Games Atari 2600 Star Gunner NoisyNet-Dueling Score 75867 #20 of 43 Archive leaderboard report
Atari Games Atari 2600 Surround NoisyNet-Dueling Score 10 #1 of 15 Archive leaderboard report
Atari Games Atari 2600 Tennis NoisyNet-Dueling Score 0 #26 of 43 Archive leaderboard report
Atari Games Atari 2600 Time Pilot NoisyNet-Dueling Score 17301 #14 of 44 Archive leaderboard report
Atari Games Atari 2600 Tutankham NoisyNet-Dueling Score 269 #14 of 44 Archive leaderboard report
Atari Games Atari 2600 Up and Down NoisyNet-Dueling Score 61326 #20 of 44 Archive leaderboard report
Atari Games Atari 2600 Venture NoisyNet-Dueling Score 815 #19 of 55 Archive leaderboard report
Atari Games Atari 2600 Video Pinball NoisyNet-Dueling Score 870954 #7 of 42 Archive leaderboard report
Atari Games Atari 2600 Wizard of Wor NoisyNet-Dueling Score 9149 #23 of 41 Archive leaderboard report
Atari Games Atari 2600 Yars Revenge NoisyNet-Dueling Score 86101 #10 of 17 Archive leaderboard report
Atari Games Atari 2600 Zaxxon NoisyNet-Dueling Score 14874 #17 of 41 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: Noisy Linear Layer, NoisyNet-A3C, NoisyNet-DQN, NoisyNet-Dueling

A3CConvolutionDQNDense ConnectionsDouble Q-learningDueling NetworkEntropy RegularizationNoisy Linear LayerNoisyNet-A3CNoisyNet-DQNNoisyNet-DuelingQ-LearningSoftmax

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