Papers › World Models

World Models

27 Mar 2018arXiv:1803.10122archive 2025-07-28

David Ha, Jürgen Schmidhuber

We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the environment. By using features extracted from the world model as inputs to an agent, we can train a very compact and simple policy that can solve the required task. We can even train our agent entirely inside of its own hallucinated dream generated by its world model, and transfer this policy back into the actual environment. An interactive version of this paper is available at https://worldmodels.github.io/

PaperPDFCodeCode 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 38 code samples harvested from 11 repositories linked to this paper: 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 17 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 38 samples from 11 repositories, 21 ran (16 with no instrument failure; 5 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

AdeelMufti/WorldModels mentioned on GitHubSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
AppliedDataSciencePartners/WorldModels mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
B-C-WANG/ReinforcementLearningInAutoPilot mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning to Drive in a Day (arXiv:1807.00412; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
Deepest-Project/WorldModels-A3C mentioned on GitHubpytorchSyntology: not harvested report
SaremS/WorldModel mentioned on GitHubSyntology: not harvested report
Veloc1tyE/Drift mentioned on GitHubpytorchMITSyntology: not harvested report
arunavkonwar/world-models mentioned on GitHubMITSyntology: 11 samples, 8 ran (1 instrument-failed) · 3 unverified report
cataluna84/WorldModels_v1.0 mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
doty-k/world_models mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
gunjan99/Review-of-World-Models-using-Latex mentioned on GitHubSyntology: not harvested report
hardmaru/WorldModelsExperiments mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
hdilab/world_model_experiments mentioned on GitHubpytorchSyntology: not harvested report
hsgrandhi/AIProject mentioned on GitHubtfMITSyntology: 7 samples, 4 ran (0 instrument-failed) · 3 unverified report
neuroevolution-ai/ProcgenAutoencoder mentioned on GitHubpytorchMITSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report
samuel500/World-Models mentioned on GitHubtfSyntology: not harvested report
susanwe/ope_worldmodels mentioned on GitHubSyntology: not harvested report
syigzaw/WorldModels mentioned on GitHubtfSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
tegg89/paper-notes mentioned on GitHubSyntology: not harvested report
yueqiw/gqn-world-model mentioned on GitHubpytorchSyntology: not harvested report
yycdavid/program-synthesis-guided-rl mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Program Synthesis Guided Reinforcement Learning for Partially Observed Environments (arXiv:2102.11137; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
zacwellmer/worldmodels mentioned on GitHubtfMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
ctallec/world-models pytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 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

38 samples harvested: 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 17 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
2ran · our draft was wrong
3ran; the contract check could not run
15ran
17unverified

Licence: 3 of the 38 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 11 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.

AdeelMufti/WorldModels community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
transform_to_weights controller.py ran · our draft was wrong no licence file found · pointer only · 4e3986fb8c3d3072 · report fixture: signature args:Args/0/?, parameters:Tensor/1/float · returned tuple · level recorded 2026-09-22
AppliedDataSciencePartners/WorldModels community (archive-listed) 1 sample, 0 ran · 1 unverified
import_data in 5 papers 02_train_vae.py unverified MIT (permissive) · 3ccd0377db51a3a2 · report
arunavkonwar/world-models community (archive-listed) 11 samples, 8 ran (1 instrument-failed) · 3 unverified
activations controller/arch.py ran fingerprinted MIT (permissive) · 7002201281413ed7 · report fixture: signature a:ndarray/1/float · returned ndarray · level recorded 2026-09-26
adjust_obs config.py ran fingerprinted MIT (permissive) · 779b4d674e5259e8 · report fixture: signature obs:ndarray/3/int · returned ndarray · level recorded 2026-09-26
compute_centered_ranks in 6 papers es.py ran fingerprinted MIT (permissive) · ca7653e52833d6c9 · report fixture: signature x:ndarray/1/float · returned ndarray · level recorded 2026-09-26
compute_ranks in 8 papers es.py ran fingerprinted MIT (permissive) · eb0179d8567680a5 · report fixture: signature x:ndarray/1/float · returned ndarray · level recorded 2026-09-26
compute_weight_decay es.py ran MIT (permissive) · 9a15dba37b6cc854 · report fixture: signature weight_decay:float/0/float, model_param_list:list/1/ndarray · returned ndarray · level recorded 2026-09-26
encode_result_packet 05_train_controller.py ran · honoured contract fingerprinted MIT (permissive) · 91277656d56a208d · report fixture: signature results:ndarray/2/float · returned ndarray · level recorded 2026-09-22
encode_solution_packets 05_train_controller.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · 8b59cd0f4edbb9e3 · report fixture: signature seeds:list/1/int, solutions:list/1/ndarray, train_mode:int/0/int, max_len:int/0/int · returned list · level recorded 2026-09-22
generate_data_action config.py ran MIT (permissive) · 714eb9398f748fd8 · report fixture: signature t:int/0/int, current_action:ndarray/1/float · returned ndarray · level recorded 2026-09-26
decode_solution_packet 05_train_controller.py unverified MIT (permissive) · 11d42d7e546811b9 · report
get_mixture_coef rnn/arch.py unverified MIT (permissive) · 28da1053026f85e4 · report
tf_normal rnn/arch.py unverified MIT (permissive) · 18d3a7c10dd43aba · report
cataluna84/WorldModels_v1.0 community (archive-listed) 1 sample, 0 ran · 1 unverified
compress_input_dct model.py unverified MIT (permissive) · a3f20419e166eba8 · report
doty-k/world_models community (archive-listed) 1 sample, 0 ran · 1 unverified
evaluate in 514 papers 05_cmaes.py unverified no licence file found · pointer only · 704c9042ecbb6026 · report
hardmaru/WorldModelsExperiments community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_pi_idx carracing/dream_env.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 7bb85eb640efb52d · report fixture: signature x:float/0/float, pdf:ndarray/1/float · returned int · level recorded 2026-09-22
hsgrandhi/AIProject community (archive-listed) 7 samples, 4 ran (0 instrument-failed) · 3 unverified
adjust_reward config.py ran fingerprinted MIT (permissive) · ad92bf94d88369c2 · report fixture: signature reward:float/0/float · returned int · level recorded 2026-09-26
encode_episode 03_generate_rnn_data.py ran MIT (permissive) · 3c6e387c07be249c · report fixture: signature vae:callable/0/?, episode:dict/0/? · returned tuple · level recorded 2026-09-26
generate_data_action config.py ran MIT (permissive) · b3600b6b2de788c6 · report fixture: signature t:int/0/int, env:MockEnv/0/? · returned ndarray · level recorded 2026-09-26
random_batch 04_train_rnn.py ran MIT (permissive) · ec5eb98a69771c02 · report fixture: signature filelist:list/1/str, batch_size:int/0/int · returned tuple · level recorded 2026-09-26
get_filelist 03_generate_rnn_data.py unverified MIT (permissive) · 066bfb0d1b959e58 · report
get_filelist 04_train_rnn.py unverified MIT (permissive) · cc59f9b3187428d7 · report
make_env in 50 papers env.py unverified MIT (permissive) · ba7be13bc51628c9 · report
neuroevolution-ai/ProcgenAutoencoder community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
create_folder_structure autoencoder_training.py ran MIT (permissive) · 9db304a7e5497d3f · report fixture: signature directory:str/0/str, name_model:str/0/str · returned tuple · level recorded 2026-09-26
has_blue_locks data_generation/balance_data.py unverified MIT (permissive) · 4b115a9b004a9253 · report
has_green_locks data_generation/balance_data.py unverified MIT (permissive) · 7f17768a58cc204c · report
has_red_locks data_generation/balance_data.py unverified MIT (permissive) · cb437d8f62056d67 · report
setup_optimizer in 15 papers autoencoder_training.py unverified MIT (permissive) · 2216d05b615869fb · report
syigzaw/WorldModels community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
encode_solution_packets 05_train_controller.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · 58a68c3a2f6830b4 · report fixture: signature seeds:list/1/int, solutions:list/1/list, max_len:int/0/int · returned list · level recorded 2026-09-22
decode_solution_packet 05_train_controller.py unverified MIT (permissive) · 42793235c6805dbf · report
import_data in 5 papers 02_train_vae.py unverified MIT (permissive) · 3c54adf8acefdb36 · report
zacwellmer/worldmodels community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
clip in 31 papers WorldModels/controller.py ran fingerprinted MIT (permissive) · b394fa6e4fc0c392 · report fixture: signature x:ndarray/2/float, lo:float/0/float, hi:float/0/float · returned ndarray · level recorded 2026-09-26
rnn_init_state WorldModels/rnn/rnn.py ran MIT (permissive) · 538f1e121b607eaa · report fixture: signature rnn:callable/0/? · returned EagerTensor · level recorded 2026-09-26
rnn_next_state WorldModels/rnn/rnn.py ran MIT (permissive) · 5ea606248ef1a89e · report fixture: signature rnn:MockRNN/0/?, z:EagerTensor/1/float, a:EagerTensor/1/float, prev_state:list/1/EagerTensor · returned list · level recorded 2026-09-26
simulate in 17 papers WorldModels/controller.py ran MIT (permissive) · bb98d1b55f68375e · report fixture: signature controller:SimpleController/0/?, env:SimpleEnv/0/?, train_mode:bool/0/bool, render_mode:bool/0/bool, num_episode:int/0/int, seed:int/0/int, max_len:int/0/int · returned tuple · level recorded 2026-09-26
make_controller WorldModels/controller.py unverified MIT (permissive) · 762af0bdb7aa9fb5 · report
ctallec/world-models community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
loss_function in 62 papers
census: 7 implementations from 6 papers, 7 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
trainvae.py ran · our draft was wrong fingerprinted MIT (permissive) · 46304a89b6b8c121 · report fixture: signature recon_x:Tensor/2/float, x:Tensor/2/float, mu:Tensor/2/float, logsigma:Tensor/2/float · returned Tensor · level recorded 2026-09-22
evaluate in 514 papers traincontroller.py unverified MIT (permissive) · ed841132809e417a · report

Tasks

Car RacingReinforcement LearningReinforcement Learning (RL)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