Papers › Curiosity-driven Exploration by Self-supervised Prediction
Curiosity-driven Exploration by Self-supervised Prediction
Deepak Pathak, Pulkit Agrawal, Alexei A. Efros, Trevor Darrell
In many real-world scenarios, rewards extrinsic to the agent are extremely sparse, or absent altogether. In such cases, curiosity can serve as an intrinsic reward signal to enable the agent to explore its environment and learn skills that might be useful later in its life. We formulate curiosity as the error in an agent's ability to predict the consequence of its own actions in a visual feature space learned by a self-supervised inverse dynamics model. Our formulation scales to high-dimensional continuous state spaces like images, bypasses the difficulties of directly predicting pixels, and, critically, ignores the aspects of the environment that cannot affect the agent. The proposed approach is evaluated in two environments: VizDoom and Super Mario Bros. Three broad settings are investigated: 1) sparse extrinsic reward, where curiosity allows for far fewer interactions with the environment to reach the goal; 2) exploration with no extrinsic reward, where curiosity pushes the agent to explore more efficiently; and 3) generalization to unseen scenarios (e.g. new levels of the same game) where the knowledge gained from earlier experience helps the agent explore new places much faster than starting from scratch. Demo video and code available at https://pathak22.github.io/noreward-rl/
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="1705.05363")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1705.05363", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1705.05363")
Code
Syntology 32 code samples harvested from 8 repositories linked to this paper: 16 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 16 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 9 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 23 samples from 7 repositories, 14 ran (13 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:
- microsoft/strategically_efficient_rl, community (archive-listed): harvested for another paper, listed under the repository
- opendilab/DI-engine, community (archive-listed): harvested for 4 other papers, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
13 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
32 samples harvested: 16 ran (of which 9 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 16 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: 14 of the 32 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 8 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 3 samples that ran, the graph records a signature this page does not show, each row saying why in its tooltip: for 2, 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; for 1, an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket src/model.py ran · our draft was wrong fingerprinted licence not identified · pointer only ·
1e1712b2e9449aaf · report
fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22 ef2d50dfca29c664 · report
fixture: signature std:float/0/float · returned function · level recorded 2026-09-22 04f384021bf36c16 · report
6ffcacf01ffe178d · report
c1b7daeed6d2b9e9 · report
e7a1c44e11ed6cd4 · report
5c333bb36f41c257 · report
5b6438137a225b8d · report
fixture: returned ICM · level recorded 2026-09-22 9696b7f33a054798 · report
fixture: returned MLP · level recorded 2026-09-22 3f01f9fd0d0c237e · report
fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-22 b48b1abd03b5ec79 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 8619d73b13d5fe9c · report
fixture: returned ICMHook · level recorded 2026-09-22 42225a852b4a6243 · report
fixture: returned bool · level recorded 2026-09-22 afccd3d581fb2a92 · report
1b90a31387361fca · report
44bab3885583f1cf · report
ae87872e3b4545e5 · report
ac63e232c69fbf8c · report
46710f2ad24953b0 · report
fixture: returned AdversarialHead · level recorded 2026-09-22 1a22d19c10546a0b · report
fixture: returned AttentionNet · level recorded 2026-09-22 census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket src/model.py ran MIT (permissive) ·
2b0ee11dc19980df · report
fixture: returned ConvBlock · level recorded 2026-09-22 2e0b24810358c532 · report
fixture: returned FeatureEncoderNet · level recorded 2026-09-22 205d70f6f65dd81d · report
fixture: returned ForwardNet · level recorded 2026-09-22 9619969eae1d3dbd · report
fixture: returned InverseNet · level recorded 2026-09-22 87da60c05cf5addb · report
fixture: signature module:callable/0/?, weight_init:callable/0/?, bias_init:callable/0/?, gain:float/0/float · returned Linear · level recorded 2026-09-22 2363a32e04cbd544 · report
fixture: signature state:Tensor/4/float, next_state:Tensor/4/float, action:Tensor/2/float · returned tuple · level recorded 2026-09-24 daf6ee6540df66a0 · 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.
8 assemblies on this paper: 8 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
8 sibling assemblies for Curiosity-driven Exploration by Self-supervised Prediction (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Curiosity-driven Exploration by Self-supervised Prediction (graph method: Curiosity-driven Exploration by Self-supervised Prediction). 3 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) · 0 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- ICM entry · level 1 · ran ·
5b6438137a225b8d - MLP model · level 1 · ran ·
9696b7f33a054798 - fanin_init helper · level 1 · ran · honoured contract ·
3f01f9fd0d0c237e
harvested Assembly for Curiosity-driven Exploration by Self-supervised Prediction (graph method: Curiosity-driven Exploration by Self-supervised Prediction). 3 bricks; individually on a fixture: 2 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; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- ICMHook entry · level 1 · ran ·
8619d73b13d5fe9c - get_numpy helper · level 1 · ran · honoured contract ·
c03dde4a55ed93b3 - tensor helper · level 0 · unverified ·
e98f92e9afd0ddda
harvested Assembly for Curiosity-driven Exploration by Self-supervised Prediction (graph method: Curiosity-driven Exploration by Self-supervised Prediction). 10 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- ICMNet entry · level 0 · unverified ·
1fea1990793e8df1 - AdversarialHead model · level 1 · ran ·
46710f2ad24953b0 - AttentionNet helper · level 1 · ran ·
1a22d19c10546a0b - AttentionTarget helper · level 0 · unverified ·
cfd8da083f2cce43 - AttentionType helper · level 0 · unverified ·
5ca07acad5f7b984 - FeatureEncoderNet model · level 1 · ran ·
2e0b24810358c532 - ForwardNet model · level 1 · ran ·
205d70f6f65dd81d - InverseNet model · level 1 · ran ·
9619969eae1d3dbd - ConvBlock helper · level 1 · ran ·
2b0ee11dc19980df - init helper · level 1 · ran · our draft was wrong ·
87da60c05cf5addb
harvested Assembly for Curiosity-driven Exploration by Self-supervised Prediction (graph method: Curiosity-driven Exploration by Self-supervised Prediction). 5 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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- Model entry · level 0 · unverified ·
afccd3d581fb2a92 - conv helper · level 0 · unverified ·
1b90a31387361fca - count_total_parameters helper · level 0 · unverified ·
44bab3885583f1cf - dense helper · level 0 · unverified ·
ae87872e3b4545e5 - has_image_observations helper · level 1 · ran · violated contract ·
42225a852b4a6243
harvested Assembly for Curiosity-driven Exploration by Self-supervised Prediction (graph method: Curiosity-driven Exploration by Self-supervised Prediction). 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.
one of 8 siblings
- ICMModel entry · level 0 · unverified ·
ac63e232c69fbf8c - Flatten helper · level 1 · ran ·
d45cd0dd13f0cbc5
harvested Assembly for Curiosity-driven Exploration by Self-supervised Prediction (graph method: Curiosity-driven Exploration by Self-supervised Prediction). 8 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- ICM entry · level 0 · unverified ·
daf6ee6540df66a0 - ICMNetwork model · level 1 · ran ·
2363a32e04cbd544 - IntrinsicReward helper · level 0 · unverified ·
a04129b701562203 - build_sequential helper · level 1 · ran; the contract check could not run ·
147627e47de141ae - prod helper · level 1 · ran · violated contract ·
2fe739431c704a67 - flatten helper · level 1 · ran · our draft was wrong ·
df69c0a5d85d8bc3 - Flatten helper · level 1 · ran ·
dca1bdd65a0d90e0 - init helper · level 1 · ran · our draft was wrong ·
9de355e93051e4ad
harvested Assembly for Curiosity-driven Exploration by Self-supervised Prediction (graph method: Curiosity-driven Exploration by Self-supervised Prediction). 9 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) · 7 unverified. The assembly has not been run end-to-end.
one of 8 siblings
- StateActionPredictor entry · level 0 · unverified ·
04f384021bf36c16 - doomHead helper · level 0 · unverified ·
7608da5b7e7f57d5 - linear model · level 0 · unverified ·
c1b7daeed6d2b9e9 - natureHead helper · level 0 · unverified ·
e7a1c44e11ed6cd4 - nipsHead helper · level 0 · unverified ·
2e17ce27bfd53d7f - normalized_columns_initializer helper · level 1 · ran · our draft was wrong ·
ef2d50dfca29c664 - universeHead model · level 0 · unverified ·
5c333bb36f41c257 - conv2d model · level 0 · unverified ·
6ffcacf01ffe178d - flatten helper · level 1 · ran · our draft was wrong ·
1e1712b2e9449aaf
harvested Assembly for Curiosity-driven Exploration by Self-supervised Prediction (graph method: Curiosity-driven Exploration by Self-supervised Prediction). 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.
one of 8 siblings
- Exploration_Policy entry · level 1 · ran ·
b48b1abd03b5ec79
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="1705.05363") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
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