Papers › CURL: Contrastive Unsupervised Representations for Reinforcement Learning

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

8 Apr 2020arXiv:2004.04136archive 2025-07-28

Aravind Srinivas, Michael Laskin, Pieter Abbeel

We present CURL: Contrastive Unsupervised Representations for Reinforcement Learning. CURL extracts high-level features from raw pixels using contrastive learning and performs off-policy control on top of the extracted features. CURL outperforms prior pixel-based methods, both model-based and model-free, on complex tasks in the DeepMind Control Suite and Atari Games showing 1.9x and 1.2x performance gains at the 100K environment and interaction steps benchmarks respectively. On the DeepMind Control Suite, CURL is the first image-based algorithm to nearly match the sample-efficiency of methods that use state-based features. Our code is open-sourced and available at https://github.com/MishaLaskin/curl.

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 8 code samples harvested from 3 repositories linked to this paper: 7 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; 5 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 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: official repository: 6 samples from 1 repository, 6 ran (2 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 2 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 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 7 samples that ran have no recorded date.

MishaLaskin/curl officialmentioned in paperpytorchMITSyntology: 6 samples, 6 ran (4 instrument-failed) · 0 unverified report
KarlXing/RL-Visual-Continuous-Control mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
aravindsrinivas/curl_rainbow mentioned on GitHubpytorchMITSyntology: not harvested report
asparius/barlowrl mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
gijskoning/ReproducingCURL mentioned on GitHubpytorchSyntology: not harvested report
microsoft/Mask-based-Latent-Reconstruction mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mask-based Latent Reconstruction for Reinforcement Learning (arXiv:2201.12096; that paper's own run record: 8 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 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

8 samples harvested: 7 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; 5 where Syntology's instrument failed) · 1 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.

3ran · our draft was wrong
2ran; the contract check could not run
2ran
1unverified

Licence: 3 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

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

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

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

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

MishaLaskin/curl official repository 6 samples, 6 ran (4 instrument-failed) · 0 unverified
gaussian_logprob in 17 papers curl_sac.py ran · our draft was wrong fingerprinted MIT (permissive) · daa7b3a0355eb7c3 · report fixture: signature noise:Tensor/2/float, log_std:Tensor/2/float · returned Tensor · level recorded, date not recorded
make_dir in 27 papers utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 42958997018c3581 · report fixture: signature dir_path:str/0/str · returned str · level recorded 2026-09-22
make_encoder in 15 papers encoder.py ran MIT (permissive) · cd7d4d2ebf4b04c8 · 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 2026-09-25
module_hash in 6 papers utils.py ran MIT (permissive) here; the stored copy is pointer only · 63cc0b17d508c362 · report fixture: signature module:callable/0/? · returned float · level recorded 2026-09-24
preprocess_obs in 8 papers utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 975f23eeea267e55 · report fixture: signature obs:Tensor/4/float, bits:int/0/int · returned Tensor · level recorded 2026-09-22
squash in 30 papers
census: 8 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
curl_sac.py ran · our draft was wrong fingerprinted MIT (permissive) · e4f442d1770eacd1 · report fixture: signature mu:Tensor/2/float, pi:Tensor/2/float, log_pi:Tensor/2/float · returned tuple · level recorded, date not recorded
KarlXing/RL-Visual-Continuous-Control community (archive-listed) 1 sample, 0 ran · 1 unverified
CURL src/agent/curl.py unverified MIT (permissive) · b87a008932a30bc3 · report
asparius/barlowrl community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
off_diagonal in 22 papers agent.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 3e30d88eaef01190 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded

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 CURL (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for CURL (graph method: CURL). 3 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. CURL entry · level 0 · unverified · b87a008932a30bc3
  2. SAC helper · level 1 · ran · bf3db7327a139e28
  3. center_crop_image helper · level 1 · ran; the contract check could not run · 31e6960f8b942b0d

harvested Assembly for CURL (graph method: CURL). 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 2 siblings

  1. CURL entry · level 1 · ran · a551a31aced2e8ed

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="2004.04136") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Atari GamesAtari Games 100kContinuous ControlContrastive LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Atari Games Atari 2600 Alien CURL Score 1148.2 #37 of 49 Archive leaderboard report
Atari Games Atari 2600 Amidar CURL Score 232.3 #36 of 48 Archive leaderboard report
Atari Games Atari 2600 Assault CURL Score 543.7 #43 of 45 Archive leaderboard report
Atari Games Atari 2600 Asterix CURL Score 524.3 #48 of 49 Archive leaderboard report
Atari Games Atari 2600 Bank Heist CURL Score 193.7 #41 of 45 Archive leaderboard report
Atari Games Atari 2600 Battle Zone CURL Score 11208 #44 of 47 Archive leaderboard report
Atari Games Atari 2600 Boxing CURL Score 4.8 #45 of 45 Archive leaderboard report
Atari Games Atari 2600 Breakout CURL Score 18.2 #52 of 58 Archive leaderboard report
Atari Games Atari 2600 Chopper Command CURL Score 1198 #43 of 45 Archive leaderboard report
Atari Games Atari 2600 Crazy Climber CURL Score 27805.6 #44 of 49 Archive leaderboard report
Atari Games Atari 2600 Demon Attack CURL Score 834 #43 of 46 Archive leaderboard report
Atari Games Atari 2600 Freeway CURL Score 27.9 #41 of 59 Archive leaderboard report
Atari Games Atari 2600 Frostbite CURL Score 924 #35 of 53 Archive leaderboard report
Atari Games Atari 2600 Gopher CURL Score 801.4 #42 of 43 Archive leaderboard report
Atari Games Atari 2600 HERO CURL Score 6235.1 #43 of 44 Archive leaderboard report
Atari Games Atari 2600 James Bond CURL Medium Human-Normalized Score 400.1 #45 of 45 Archive leaderboard report
Atari Games Atari 2600 Kangaroo CURL Score 345.3 #42 of 47 Archive leaderboard report
Atari Games Atari 2600 Krull CURL Score 3833.6 #41 of 45 Archive leaderboard report
Atari Games Atari 2600 Kung-Fu Master CURL Score 14280 #42 of 43 Archive leaderboard report
Atari Games Atari 2600 Ms. Pacman CURL Score 1492.8 #38 of 47 Archive leaderboard report
Atari Games Atari 2600 Pong CURL Score 2.1 #49 of 52 Archive leaderboard report
Atari Games Atari 2600 Private Eye CURL Score 105.2 #41 of 52 Archive leaderboard report
Atari Games Atari 2600 Q*Bert CURL Score 1225.6 #49 of 57 Archive leaderboard report
Atari Games Atari 2600 Road Runner CURL Score 6786.7 #41 of 44 Archive leaderboard report
Atari Games Atari 2600 Seaquest CURL Score 408 #53 of 57 Archive leaderboard report
Atari Games Atari 2600 Up and Down CURL Score 2735.2 #42 of 44 Archive leaderboard report
Continuous Control Ball in cup, catch (DMControl100k) CURL Score 769 #1 of 1 Archive leaderboard report
Continuous Control Ball in cup, catch (DMControl500k) CURL Score 959 #1 of 1 Archive leaderboard report
Continuous Control Cartpole, swingup (DMControl100k) CURL Score 582 #1 of 1 Archive leaderboard report
Continuous Control Cartpole, swingup (DMControl500k) CURL Score 841 #1 of 1 Archive leaderboard report
Continuous Control Cheetah, run (DMControl100k) CURL Score 299 #1 of 1 Archive leaderboard report
Continuous Control Cheetah, run (DMControl500k) CURL Score 518 #1 of 1 Archive leaderboard report
Continuous Control Finger, spin (DMControl100k) CURL Score 767 #1 of 1 Archive leaderboard report
Continuous Control Finger, spin (DMControl500k) CURL Score 926 #1 of 1 Archive leaderboard report
Continuous Control Reacher, easy (DMControl100k) CURL Score 538 #1 of 1 Archive leaderboard report
Continuous Control Reacher, easy (DMControl500k) CURL Score 929 #1 of 1 Archive leaderboard report
Continuous Control Walker, walk (DMControl100k) CURL Score 403 #1 of 1 Archive leaderboard report
Continuous Control Walker, walk (DMControl500k) CURL Score 902 #1 of 1 Archive leaderboard report

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

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