Papers › Curiosity-driven Exploration by Self-supervised Prediction

Curiosity-driven Exploration by Self-supervised Prediction

15 May 2017ICML 2017 8arXiv:1705.05363archive 2025-07-28

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/

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1705.05363")

Code

Syntology Ran 16 of 32 code samples harvested from 8 repositories linked to this paper; 16 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 3 ran · our draft was wrong; 11 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 2 ran; community (archive-listed): 23 samples from 7 repositories, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

HaozheJasper/CBRL_KDD22 mentioned on GitHubpytorch report
RLAgent/state-marginal-matching mentioned on GitHubpytorch report
adik993/ppo-pytorch mentioned on GitHubpytorch report
alex-petrenko/curious-rl mentioned on GitHub report
lgerrets/rl18-curiosity mentioned on GitHub report
microsoft/strategically_efficient_rl mentioned on GitHubtfMIT report
opendilab/DI-engine mentioned on GitHubpytorch report
rpatrik96/AttA2C mentioned on GitHubpytorch report
uoe-agents/derl mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

32 samples harvested; 16 ran; 1 honoured the contract we drafted; 16 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
11ran
16unverified

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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

flatten pathak22/noreward-rl/src/model.py official repository ran · our draft was wrong fingerprinted licence not identified · pointer only · 1e1712b2e9449aaf · report
normalized_columns_initializer pathak22/noreward-rl/src/model.py official repository ran · our draft was wrong licence not identified · pointer only · ef2d50dfca29c664 · report
StateActionPredictor pathak22/noreward-rl/src/model.py official repository unverified licence not identified · pointer only · 04f384021bf36c16 · report
conv2d pathak22/noreward-rl/src/model.py official repository unverified licence not identified · pointer only · 6ffcacf01ffe178d · report
doomHead pathak22/noreward-rl/src/model.py official repository unverified licence not identified · pointer only · 7608da5b7e7f57d5 · report
linear pathak22/noreward-rl/src/model.py official repository unverified licence not identified · pointer only · c1b7daeed6d2b9e9 · report
natureHead pathak22/noreward-rl/src/model.py official repository unverified licence not identified · pointer only · e7a1c44e11ed6cd4 · report
nipsHead pathak22/noreward-rl/src/model.py official repository unverified licence not identified · pointer only · 2e17ce27bfd53d7f · report
universeHead pathak22/noreward-rl/src/model.py official repository unverified licence not identified · pointer only · 5c333bb36f41c257 · report
AdversarialHead rpatrik96/AttA2C/src/model.py community (archive-listed) ran MIT (permissive) · 46710f2ad24953b0 · report
AttentionNet rpatrik96/AttA2C/src/model.py community (archive-listed) ran fingerprinted MIT (permissive) · 1a22d19c10546a0b · report
ConvBlock rpatrik96/AttA2C/src/model.py community (archive-listed) ran MIT (permissive) · 2b0ee11dc19980df · report
Exploration_Policy MaxLikesMath/Adventures-In-Reinforcement-Learning/CuriousityDrivenLearning/CartpoleCuriosity.py community (archive-listed) ran fingerprinted MIT (permissive) · b48b1abd03b5ec79 · report
FeatureEncoderNet rpatrik96/AttA2C/src/model.py community (archive-listed) ran MIT (permissive) · 2e0b24810358c532 · report
ForwardNet rpatrik96/AttA2C/src/model.py community (archive-listed) ran MIT (permissive) · 205d70f6f65dd81d · report
ICM HaozheJasper/CBRL_KDD22/python/model.py community (archive-listed) ran · metamorphic tier: deterministic no licence file found · pointer only · 5b6438137a225b8d · report
ICMHook RLAgent/state-marginal-matching/rlkit/torch/intrinsic/icm_hook.py community (archive-listed) ran MIT (permissive) · 8619d73b13d5fe9c · report
ICMNetwork uoe-agents/derl/derl/intrinsic_rewards/icm/icm.py community (archive-listed) ran fingerprinted no licence file found · pointer only · 2363a32e04cbd544 · report
InverseNet rpatrik96/AttA2C/src/model.py community (archive-listed) ran MIT (permissive) · 9619969eae1d3dbd · report
MLP HaozheJasper/CBRL_KDD22/python/model.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 9696b7f33a054798 · report
fanin_init HaozheJasper/CBRL_KDD22/python/model.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 3f01f9fd0d0c237e · report
has_image_observations alex-petrenko/curious-rl/algorithms/curious_a2c/agent_curious_a2c.py community (archive-listed) ran · violated contract MIT (permissive) · 42225a852b4a6243 · report
init rpatrik96/AttA2C/src/model.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 87da60c05cf5addb · report
AttentionTarget rpatrik96/AttA2C/src/model.py community (archive-listed) unverified MIT (permissive) · cfd8da083f2cce43 · report
AttentionType rpatrik96/AttA2C/src/model.py community (archive-listed) unverified MIT (permissive) · 5ca07acad5f7b984 · report
ICM uoe-agents/derl/derl/intrinsic_rewards/icm/icm.py community (archive-listed) unverified no licence file found · pointer only · daf6ee6540df66a0 · report
ICMModel jcwleo/curiosity-driven-exploration-pytorch/model.py community (archive-listed) unverified MIT (permissive) · ac63e232c69fbf8c · report
ICMNet rpatrik96/AttA2C/src/model.py community (archive-listed) unverified MIT (permissive) · 1fea1990793e8df1 · report
Model alex-petrenko/curious-rl/algorithms/curious_a2c/agent_curious_a2c.py community (archive-listed) unverified MIT (permissive) · afccd3d581fb2a92 · report
conv alex-petrenko/curious-rl/algorithms/curious_a2c/agent_curious_a2c.py community (archive-listed) unverified MIT (permissive) · 1b90a31387361fca · report
count_total_parameters alex-petrenko/curious-rl/algorithms/curious_a2c/agent_curious_a2c.py community (archive-listed) unverified MIT (permissive) · 44bab3885583f1cf · report
dense alex-petrenko/curious-rl/algorithms/curious_a2c/agent_curious_a2c.py community (archive-listed) unverified MIT (permissive) · ae87872e3b4545e5 · report

Tasks

PredictionUnsupervised Reinforcement Learning

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