Papers › Reinforcement Learning with Augmented Data

Reinforcement Learning with Augmented Data

30 Apr 2020NeurIPS 2020 12arXiv:2004.14990archive 2025-07-28

Michael Laskin, Kimin Lee, Adam Stooke, Lerrel Pinto, Pieter Abbeel, Aravind Srinivas

Learning from visual observations is a fundamental yet challenging problem in Reinforcement Learning (RL). Although algorithmic advances combined with convolutional neural networks have proved to be a recipe for success, current methods are still lacking on two fronts: (a) data-efficiency of learning and (b) generalization to new environments. To this end, we present Reinforcement Learning with Augmented Data (RAD), a simple plug-and-play module that can enhance most RL algorithms. We perform the first extensive study of general data augmentations for RL on both pixel-based and state-based inputs, and introduce two new data augmentations - random translate and random amplitude scale. We show that augmentations such as random translate, crop, color jitter, patch cutout, random convolutions, and amplitude scale can enable simple RL algorithms to outperform complex state-of-the-art methods across common benchmarks. RAD sets a new state-of-the-art in terms of data-efficiency and final performance on the DeepMind Control Suite benchmark for pixel-based control as well as OpenAI Gym benchmark for state-based control. We further demonstrate that RAD significantly improves test-time generalization over existing methods on several OpenAI ProcGen benchmarks. Our RAD module and training code are available at https://www.github.com/MishaLaskin/rad.

PaperPDFConference PDFCodeCode 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 24 code samples harvested from 2 repositories linked to this paper: 21 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 9 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: named in the paper: 21 samples from 1 repository, 18 ran (7 with no instrument failure; 11 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 3 ran (2 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 1 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.

MishaLaskin/rad mentioned in paperpytorchSyntology: 21 samples, 18 ran (11 instrument-failed) · 3 unverified report
KarlXing/RL-Visual-Continuous-Control mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified 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

24 samples harvested: 21 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 12 where Syntology's instrument failed) · 3 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.

1ran · honoured contract
3ran · our draft was wrong
9ran; the contract check could not run
8ran
3unverified

Licence: 21 of the 24 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample 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.

MishaLaskin/rad named in the paper 21 samples, 18 ran (11 instrument-failed) · 3 unverified
Actor in 68 papers curl_sac.py ran no licence file found · pointer only · 5aaa7c97de18af3a · report fixture: returned Actor · level recorded 2026-09-22
CURL curl_sac.py ran no licence file found · pointer only · a551a31aced2e8ed · report fixture: returned CURL · level recorded 2026-09-22
ColorJitterLayer curl_sac.py ran no licence file found · pointer only · 7eeb6c2c86ebd37d · report fixture: returned ColorJitterLayer · level recorded 2026-09-22
Critic in 60 papers curl_sac.py ran no licence file found · pointer only · faa8d44dfeaada9d · report fixture: returned Critic · level recorded 2026-09-22
IdentityEncoder curl_sac.py ran fingerprinted no licence file found · pointer only · 8b06f5d9a377410d · report fixture: returned IdentityEncoder · level recorded 2026-09-22
PixelEncoder in 5 papers curl_sac.py ran no licence file found · pointer only · 75ea19a7c991ff1d · report fixture: returned PixelEncoder · level recorded 2026-09-22
grayscale curl_sac.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 1bb28d88e7ae1e71 · report fixture: signature imgs:Tensor/4/float · returned Tensor · level recorded 2026-09-22
hsv2rgb in 5 papers curl_sac.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 718e1902f65f1be2 · report fixture: signature hsv:Tensor/4/float · returned Tensor · level recorded 2026-09-22
make_encoder in 15 papers curl_sac.py ran · our draft was wrong no licence file found · pointer only · 3ff1a7cb98f67025 · report fixture: signature encoder_type:str/0/str, obs_shape:tuple/1/int, feature_dim:int/0/int, num_layers:int/0/int, num_filters:int/0/int, output_logits:bool/0/bool · returned PixelEncoder · level recorded 2026-09-22
no_aug curl_sac.py ran · honoured contract fingerprinted no licence file found · pointer only · b1cb15a87e0863be · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
random_convolution curl_sac.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 3b7275db7d30b2b9 · report fixture: signature imgs:Tensor/4/float · returned Tensor · level recorded 2026-09-22
random_crop in 59 papers curl_sac.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · cc205ddaca3bfbbc · report fixture: signature imgs:ndarray/4/int, out:int/0/int · returned ndarray · level recorded 2026-09-22
random_cutout curl_sac.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 417e34ed0818a71b · report fixture: signature imgs:ndarray/4/int, min_cut:int/0/int, max_cut:int/0/int · returned ndarray · level recorded 2026-09-22
random_cutout_color curl_sac.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · d4841127aa83b755 · report fixture: signature imgs:ndarray/4/float, min_cut:int/0/int, max_cut:int/0/int · returned ndarray · level recorded 2026-09-22
random_flip in 12 papers curl_sac.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 0c0e4ec30cabf972 · report fixture: signature images:Tensor/4/float, p:float/0/float · returned Tensor · level recorded 2026-09-22
random_grayscale curl_sac.py ran · our draft was wrong fingerprinted no licence file found · pointer only · ef56bb771298e9ef · report fixture: signature images:Tensor/4/float, p:float/0/float · returned Tensor · level recorded 2026-09-22
random_translate curl_sac.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 77241bfa75e23abd · report fixture: signature imgs:ndarray/4/int, size:int/0/int, return_random_idxs:bool/0/bool, h1s:NoneType/0/?, w1s:NoneType/0/? · returned ndarray · level recorded 2026-09-22
rgb2hsv curl_sac.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 1c24bb2fb72c4f9d · report fixture: signature rgb:Tensor/4/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
RadSacAgent curl_sac.py unverified no licence file found · pointer only · 62d57e42506581cb · report
random_color_jitter curl_sac.py unverified no licence file found · pointer only · 5a5ab3e704f9a4cd · report
random_rotation in 15 papers curl_sac.py unverified no licence file found · pointer only · c0364ede43f86490 · report
KarlXing/RL-Visual-Continuous-Control community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
RAD src/agent/rad.py ran MIT (permissive) · 4ef6619d0e3853e4 · report fixture: returned RAD · level recorded 2026-09-22
SAC in 8 papers src/agent/rad.py ran MIT (permissive) · bf3db7327a139e28 · report fixture: returned SAC · level recorded 2026-09-22
center_crop_image src/agent/rad.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 31e6960f8b942b0d · report fixture: signature image:Tensor/3/float, output_size:int/0/int · returned Tensor · level recorded 2026-09-22

Method as code Syntology

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

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Reinforcement Learning with Augmented Data (RAD) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Reinforcement Learning with Augmented Data (RAD) (graph method: Reinforcement Learning with Augmented Data (RAD)). 3 bricks; individually on a fixture: 3 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; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. RAD entry · level 1 · ran · 4ef6619d0e3853e4
  2. SAC helper · level 1 · ran · bf3db7327a139e28
  3. center_crop_image data_transform · level 1 · ran; the contract check could not run (RAISES) · 31e6960f8b942b0d

harvested Assembly for Reinforcement Learning with Augmented Data (RAD) (graph method: Reinforcement Learning with Augmented Data (RAD)). 28 bricks; individually on a fixture: 22 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 14 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. RadSacAgent entry · level 0 · unverified · 62d57e42506581cb
  2. Actor model · level 1 · ran · 5aaa7c97de18af3a
  3. CURL model · level 1 · ran · a551a31aced2e8ed
  4. Critic model · level 1 · ran · faa8d44dfeaada9d
  5. center_crop_image helper · level 1 · ran; the contract check could not run (RAISES) · 31e6960f8b942b0d
  6. no_aug data_transform · level 1 · ran · honoured contract · b1cb15a87e0863be
  7. random_color_jitter data_transform · level 0 · unverified · 5a5ab3e704f9a4cd
  8. random_convolution data_transform · level 1 · ran; the contract check could not run (RAISES) · 3b7275db7d30b2b9
  9. random_crop data_transform · level 1 · ran; the contract check could not run (RAISES) · cc205ddaca3bfbbc
  10. random_cutout data_transform · level 1 · ran; the contract check could not run (RAISES) · 417e34ed0818a71b
  11. random_cutout_color helper · level 1 · ran; the contract check could not run (RAISES) · d4841127aa83b755
  12. random_flip data_transform · level 1 · ran; the contract check could not run (RAISES) · 0c0e4ec30cabf972
  13. random_grayscale data_transform · level 1 · ran · our draft was wrong · ef56bb771298e9ef
  14. random_rotation data_transform · level 0 · unverified · c0364ede43f86490
  15. random_translate helper · level 1 · ran; the contract check could not run (RAISES) · 77241bfa75e23abd
  16. soft_update_params helper · level 0 · unverified · bc0768cc0f4f49c7
  17. gaussian_logprob helper · level 1 · ran · our draft was wrong · daa7b3a0355eb7c3
  18. make_encoder helper · level 1 · ran · our draft was wrong · 3ff1a7cb98f67025
  19. squash helper · level 1 · ran · our draft was wrong · e4f442d1770eacd1
  20. weight_init helper · level 0 · unverified · 4a63e89d67417081
  21. QFunction model · level 1 · ran · 5447123791608219
  22. ColorJitterLayer helper · level 1 · ran · 7eeb6c2c86ebd37d
  23. grayscale helper · level 1 · ran; the contract check could not run (RAISES) · 1bb28d88e7ae1e71
  24. hsv2rgb helper · level 1 · ran · our draft was wrong · 718e1902f65f1be2
  25. rgb2hsv helper · level 1 · ran; the contract check could not run (RAISES) · 1c24bb2fb72c4f9d
  26. IdentityEncoder model · level 1 · ran · 8b06f5d9a377410d
  27. PixelEncoder model · level 1 · ran · 75ea19a7c991ff1d
  28. tie_weights helper · level 0 · unverified · fc88ef6a629962e5

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="2004.14990") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationOpenAI GymReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Dense ConnectionsEntropy RegularizationExperience ReplayPPOReLUSoft Actor Critic

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