Papers › Dream to Control: Learning Behaviors by Latent Imagination

Dream to Control: Learning Behaviors by Latent Imagination

3 Dec 2019ICLR 2020 1arXiv:1912.01603archive 2025-07-28

Danijar Hafner, Timothy Lillicrap, Jimmy Ba, Mohammad Norouzi

Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many potential ways for deriving behaviors from them. We present Dreamer, a reinforcement learning agent that solves long-horizon tasks from images purely by latent imagination. We efficiently learn behaviors by propagating analytic gradients of learned state values back through trajectories imagined in the compact state space of a learned world model. On 20 challenging visual control tasks, Dreamer exceeds existing approaches in data-efficiency, computation time, and final performance.

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 62 code samples harvested from 10 repositories linked to this paper: 52 ran (of which 33 constructed an object rather than computing a result; 45 with no instrument failure: 1 honoured, 0 violated, 44 with no contract checked; 7 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 56 samples from 9 repositories, 49 ran (42 with no instrument failure; 7 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 5 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.

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

danijar/dreamer officialmentioned on GitHubtfMITSyntology: 6 samples, 3 ran (0 instrument-failed) · 3 unverified report
AliengirlLiv/xrl-dreamer mentioned on GitHubtfMITSyntology: not harvested report
KohMat/carracing-dreamer mentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
Yizhao111/dreamer-pytorch mentioned on GitHubpytorchSyntology: 15 samples, 13 ran (3 instrument-failed) · 2 unverified report
adityabingi/Dreamer mentioned on GitHubpytorchSyntology: 10 samples, 9 ran (1 instrument-failed) · 1 unverified report
agiachris/STAP mentioned on GitHubpytorchMITSyntology: not harvested report
chamorajg/pl-dreamer mentioned on GitHubpytorchSyntology: 9 samples, 8 ran (1 instrument-failed) · 1 unverified report
cross32768/Dreamer_PyTorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
enikhu/dreamer mentioned on GitHubtfMITSyntology: not harvested report
facebookresearch/denoised_mdp mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
google-research/dreamer mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning (arXiv:2010.12142; that paper's own run record: 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); nothing checks that they implement this paper's method. report
juliusfrost/dreamer-pytorch mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
kc-ml2/SimpleDreamer mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Planning to Explore via Self-Supervised World Models (arXiv:2005.05960; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
yusukeurakami/dreamer-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
zdhnarsil/stochastic-marginal-actor-critic mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Latent State Marginalization as a Low-cost Approach for Improving Exploration (arXiv:2210.00999; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
zhixuan-lin/dreamer-pytorch mentioned on GitHubpytorchSyntology: 11 samples, 10 ran (1 instrument-failed) · 1 unverified report
Eclectic-Sheep/sheeprl pytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
minhphd/PyDreamerV1 pytorchSyntology: not harvested 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
pytorch/rl jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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); nothing checks that they implement this paper's method. report
ray-project/ray Syntology: not harvested 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

62 samples harvested: 52 ran (of which 33 constructed an object rather than computing a result; 45 with no instrument failure: 1 honoured, 0 violated, 44 with no contract checked; 7 where Syntology's instrument failed) · 10 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
7ran · our draft was wrong
44ran
10unverified

Licence: 9 of the 62 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 10 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 8 samples 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. 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.

danijar/dreamer official repository 6 samples, 3 ran (0 instrument-failed) · 3 unverified
load_baselines in 7 papers plotting.py ran · honoured contract MIT (permissive) · 2f2cf1bbab74e2d7 · report fixture: returned list · level recorded 2026-09-22
load_run in 15 papers plotting.py ran MIT (permissive) · 8e5272c2d61dcc1d · report fixture: signature filename:PosixPath/0/?, indir:PosixPath/0/?, args:Args/0/? · returned Run · level recorded 2026-09-25
nest_summary tools.py ran MIT (permissive) · 0ff405af2200f366 · report fixture: signature structure:dict/0/? · returned dict · level recorded 2026-09-25
encode_gif in 7 papers tools.py unverified MIT (permissive) · 427c760e638127dd · report
graph_summary tools.py unverified MIT (permissive) · 1a89b7d1602aedb6 · report
load_runs in 11 papers plotting.py unverified MIT (permissive) · 6dd3eb82ea8db085 · report
KohMat/carracing-dreamer community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
apply in 10 papers dreamer/utils/apply.py ran MIT (permissive) · 956ceb6333c8ac66 · report fixture: signature data:float/0/float, func:callable/0/? · returned float · level recorded 2026-09-24
conv_out dreamer/carracing/network.py ran fingerprinted MIT (permissive) · ecebf2e9b74c28b2 · report fixture: signature h_in:int/0/int, padding:int/0/int, kernel_size:int/0/int, stride:int/0/int · returned int · level recorded 2026-09-24
conv_out_shape dreamer/carracing/network.py ran MIT (permissive) · bda617dc1839d3c5 · report fixture: signature h_in:tuple/1/int, padding:int/0/int, kernel_size:int/0/int, stride:int/0/int · returned tuple · level recorded 2026-09-24
get_parameters in 30 papers dreamer/utils/freeze_parameter.py ran MIT (permissive) · c53ea31731e9c271 · report fixture: signature modules:list/1/callable · returned list · level recorded 2026-09-24
kl_divergence_between_states dreamer/rssm.py ran MIT (permissive) · 5108b244cb3972b4 · report fixture: signature prior:State/1/Tensor, posterior:State/1/Tensor, min_nats:float/0/float, dist_type:callable/0/? · returned Tensor · level recorded 2026-09-24
output_padding dreamer/carracing/network.py ran MIT (permissive) · b733787027a71a6d · report fixture: signature h_in:int/0/int, conv_out:int/0/int, padding:int/0/int, kernel_size:int/0/int, stride:int/0/int · returned int · level recorded 2026-09-24
Yizhao111/dreamer-pytorch community (archive-listed) 15 samples, 13 ran (3 instrument-failed) · 2 unverified
ActorModel agent.py ran MIT (permissive) · 1e69bdfedcc82427 · report fixture: returned ActorModel · level recorded 2026-09-22
Encoder in 278 papers agent.py ran · our draft was wrong MIT (permissive) · 5903294d08bd52f9 · report fixture: signature symbolic:bool/0/bool, observation_size:int/0/int, embedding_size:int/0/int, activation_function:str/0/str · returned SymbolicEncoder · level recorded 2026-09-22
ObservationModel in 6 papers agent.py ran · our draft was wrong MIT (permissive) · be5a219bf8efda66 · report fixture: signature symbolic:bool/0/bool, observation_size:int/0/int, belief_size:int/0/int, state_size:int/0/int, embedding_size:int/0/int, activation_function:str/0/str · returned SymbolicObservationModel · level recorded 2026-09-22
PCONTModel agent.py ran MIT (permissive) · 9d8facfbbfad7e8e · report fixture: returned PCONTModel · level recorded 2026-09-22
RewardModel in 10 papers agent.py ran MIT (permissive) · ff12acbebe54d7cc · report fixture: returned RewardModel · level recorded 2026-09-22
SampleDist agent.py ran MIT (permissive) · 56dcf30a95968f30 · report fixture: returned SampleDist · level recorded 2026-09-22
SymbolicEncoder agent.py ran fingerprinted MIT (permissive) · 8440a6eb02fe1454 · report fixture: returned SymbolicEncoder · level recorded 2026-09-22
SymbolicObservationModel agent.py ran MIT (permissive) · 2e24f94844e096be · report fixture: returned SymbolicObservationModel · level recorded 2026-09-22
TransitionModel in 5 papers agent.py ran MIT (permissive) · 2a61bebe2088ddb9 · report fixture: returned TransitionModel · level recorded 2026-09-22
ValueModel agent.py ran MIT (permissive) · 097f32971f48a3db · report fixture: returned ValueModel · level recorded 2026-09-22
VisualEncoder agent.py ran MIT (permissive) · bf63a45ab9d6bbf2 · report fixture: returned VisualEncoder · level recorded 2026-09-22
VisualObservationModel agent.py ran MIT (permissive) · c42784e0cc95cfe0 · report fixture: returned VisualObservationModel · level recorded 2026-09-22
cal_returns agent.py ran · our draft was wrong fingerprinted MIT (permissive) · 8463fe3398301135 · report fixture: signature reward:Tensor/3/float, value:Tensor/3/float, bootstrap:Tensor/2/float, pcont:float/0/float, lambda_:float/0/float · returned Tensor · level recorded 2026-09-22
Dreamer agent.py unverified MIT (permissive) · 5d8eb8c3fb19bbac · report
bottle agent.py unverified MIT (permissive) · 25c79a6d1db5ea05 · report
adityabingi/Dreamer community (archive-listed) 10 samples, 9 ran (1 instrument-failed) · 1 unverified
ActionDecoder dreamer.py ran MIT (permissive) · 032906ec0da4a020 · report fixture: returned ActionDecoder · level recorded 2026-09-22
ConvDecoder in 6 papers dreamer.py ran MIT (permissive) · c2fb17f9cc07745b · report fixture: returned ConvDecoder · level recorded 2026-09-22
ConvEncoder in 12 papers dreamer.py ran MIT (permissive) · ea21fcd799d8f65e · report fixture: returned ConvEncoder · level recorded 2026-09-22
DenseDecoder dreamer.py ran MIT (permissive) · 9647814e70d10581 · report fixture: returned DenseDecoder · level recorded 2026-09-22
RSSM in 7 papers dreamer.py ran MIT (permissive) · 6ed93a3bd0b35bbd · report fixture: returned RSSM · level recorded 2026-09-22
ReplayBuffer in 33 papers dreamer.py ran MIT (permissive) · 9250128488be37e8 · report fixture: returned ReplayBuffer · level recorded 2026-09-22
SampleDist dreamer.py ran MIT (permissive) · f09ab92bd73f0a92 · report fixture: returned SampleDist · level recorded 2026-09-22
TanhBijector dreamer.py ran fingerprinted MIT (permissive) · e441022cca867bcd · report fixture: returned TanhBijector · level recorded 2026-09-22
preprocess_obs in 8 papers dreamer.py ran · our draft was wrong fingerprinted MIT (permissive) · b3d662dabfc89979 · report fixture: signature obs:Tensor/2/int · returned Tensor · level recorded 2026-09-22
Dreamer dreamer.py unverified MIT (permissive) · e6c80bdd218b3f8f · report
chamorajg/pl-dreamer community (archive-listed) 9 samples, 8 ran (1 instrument-failed) · 1 unverified
ActionDecoder planet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 83372b051144a5c7 · report fixture: returned ActionDecoder · level recorded 2026-09-22
Decoder in 210 papers planet.py ran · metamorphic tier: deterministic no licence file found · pointer only · feeb1770217fa3ec · report fixture: returned Decoder · level recorded 2026-09-22
DenseDecoder planet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 846d8e32c15e22b1 · report fixture: returned DenseDecoder · level recorded 2026-09-22
Encoder in 278 papers planet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 491e2697053dd0fc · report fixture: returned Encoder · level recorded 2026-09-22
RSSM in 7 papers planet.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5fd2e204f8b1686c · report fixture: returned RSSM · level recorded 2026-09-22
Reshape in 7 papers planet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 78cb080bf8cd18b0 · report fixture: returned Reshape · level recorded 2026-09-22
TanhBijector planet.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · d4396c5590abd108 · report fixture: returned TanhBijector · level recorded 2026-09-22
atanh in 10 papers
census: 3 implementations from 5 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
planet.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 094cf207447fa2a5 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
PLANet planet.py unverified no licence file found · pointer only · 8cd4d48928170685 · report
cross32768/Dreamer_PyTorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RecurrentStateSpaceModel model.py ran MIT (permissive) · 06dafb6454d57ef2 · report fixture: signature state:Tensor/2/float, action:Tensor/2/float, rnn_hidden:Tensor/2/float, embedded_next_obs:Tensor/2/float · returned tuple · level recorded 2026-09-24
juliusfrost/dreamer-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_parameters in 30 papers dreamer/utils/module.py ran MIT (permissive) · 00749ea05ebef1a6 · report fixture: signature modules:list/1/callable · returned list · level recorded 2026-09-24
yusukeurakami/dreamer-pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
TransitionModel in 5 papers models.py unverified MIT (permissive) · 28f50a7941b7cc60 · report
zhixuan-lin/dreamer-pytorch community (archive-listed) 11 samples, 10 ran (1 instrument-failed) · 1 unverified
ActionDecoder dreamer.py ran · metamorphic tier: deterministic MIT (permissive) · 0b707e9f2a68a262 · report fixture: returned ActionDecoder · level recorded 2026-09-22
AttrDict in 5 papers dreamer.py ran · metamorphic tier: deterministic MIT (permissive) · 4000edd2f154ac83 · report fixture: returned AttrDict · level recorded 2026-09-22
AverageMeter in 26 papers dreamer.py ran MIT (permissive) · 06a7b70ff704fbf8 · report fixture: returned AverageMeter · level recorded 2026-09-22
Config in 46 papers dreamer.py ran · metamorphic tier: deterministic MIT (permissive) · 36c19e60097cae7a · report fixture: returned Config · level recorded 2026-09-22
ConvDecoder in 6 papers dreamer.py ran · metamorphic tier: deterministic MIT (permissive) · 478198ae4e61532f · report fixture: returned ConvDecoder · level recorded 2026-09-22
ConvEncoder in 12 papers dreamer.py ran · metamorphic tier: deterministic MIT (permissive) · 5a3d541c43e302f3 · report fixture: returned ConvEncoder · level recorded 2026-09-22
DenseDecoder dreamer.py ran · metamorphic tier: deterministic MIT (permissive) · 9c449af65508ffc5 · report fixture: returned DenseDecoder · level recorded 2026-09-22
RSSM in 7 papers dreamer.py ran MIT (permissive) · d0fb3df4884ed3da · report fixture: signature embed:Tensor/3/float, action:Tensor/3/float, state:NoneType/0/? · returned tuple · level recorded 2026-09-24
ReplayBuffer in 33 papers dreamer.py ran MIT (permissive) · 8c761148be72a1af · report fixture: returned ReplayBuffer · level recorded 2026-09-22
freeze in 9 papers dreamer.py ran · our draft was wrong MIT (permissive) · d1d08bc76fe301d5 · report fixture: signature module:callable/0/? · returned _GeneratorContextManager · level recorded 2026-09-22
Dreamer dreamer.py unverified MIT (permissive) · af793972b29d01fd · report
Eclectic-Sheep/sheeprl community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
compute_stochastic_state sheeprl/algos/dreamer_v1/agent.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · fa76beb6fb8d8865 · report fixture: signature state_information:Tensor/2/float, event_shape:int/0/int, min_std:float/0/float · returned tuple · level recorded 2026-09-22
RSSM in 7 papers sheeprl/algos/dreamer_v1/agent.py unverified Apache-2.0 (permissive) · 6f6fbb1df0959d34 · 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.

7 assemblies on this paper: 7 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for Dreamer (graph method: Dreamer). 9 bricks; individually on a fixture: 8 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. PLANet entry · level 0 · unverified · 8cd4d48928170685
  2. ActionDecoder model · level 1 · ran · 83372b051144a5c7
  3. Decoder model · level 1 · ran · feeb1770217fa3ec
  4. DenseDecoder model · level 1 · ran · 846d8e32c15e22b1
  5. Encoder model · level 1 · ran · 491e2697053dd0fc
  6. RSSM model · level 1 · ran · 5fd2e204f8b1686c
  7. TanhBijector helper · level 1 · ran · d4396c5590abd108
  8. Reshape helper · level 1 · ran · 78cb080bf8cd18b0
  9. atanh helper · level 1 · ran · our draft was wrong · 094cf207447fa2a5

harvested Assembly for Dreamer (graph method: Dreamer). 11 bricks; individually on a fixture: 10 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. Dreamer entry · level 0 · unverified · af793972b29d01fd
  2. ActionDecoder model · level 1 · ran · 0b707e9f2a68a262
  3. AttrDict helper · level 1 · ran · 4000edd2f154ac83
  4. AverageMeter helper · level 1 · ran · 06a7b70ff704fbf8
  5. Config helper · level 1 · ran · 36c19e60097cae7a
  6. ConvDecoder model · level 1 · ran · 478198ae4e61532f
  7. ConvEncoder model · level 1 · ran · 5a3d541c43e302f3
  8. DenseDecoder model · level 1 · ran · 9c449af65508ffc5
  9. RSSM model · level 1 · ran · d0fb3df4884ed3da
  10. ReplayBuffer helper · level 1 · ran · 8c761148be72a1af
  11. freeze helper · level 1 · ran · our draft was wrong · d1d08bc76fe301d5

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

one of 7 siblings

  1. RSSM entry · level 0 · unverified · 6f6fbb1df0959d34
  2. compute_stochastic_state helper · level 1 · ran · our draft was wrong · fa76beb6fb8d8865

harvested Assembly for Dreamer (graph method: Dreamer). 15 bricks; individually on a fixture: 13 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. Dreamer entry · level 0 · unverified · 5d8eb8c3fb19bbac
  2. ActorModel model · level 1 · ran · 1e69bdfedcc82427
  3. Encoder model · level 1 · ran · our draft was wrong · 5903294d08bd52f9
  4. ObservationModel model · level 1 · ran · our draft was wrong · be5a219bf8efda66
  5. PCONTModel helper · level 1 · ran · 9d8facfbbfad7e8e
  6. RewardModel model · level 1 · ran · ff12acbebe54d7cc
  7. TransitionModel model · level 1 · ran · 2a61bebe2088ddb9
  8. ValueModel model · level 1 · ran · 097f32971f48a3db
  9. bottle helper · level 0 · unverified · 25c79a6d1db5ea05
  10. cal_returns update_rule · level 1 · ran · our draft was wrong · 8463fe3398301135
  11. SampleDist helper · level 1 · ran · 56dcf30a95968f30
  12. SymbolicEncoder model · level 1 · ran · 8440a6eb02fe1454
  13. VisualEncoder model · level 1 · ran · bf63a45ab9d6bbf2
  14. SymbolicObservationModel model · level 1 · ran · 2e24f94844e096be
  15. VisualObservationModel model · level 1 · ran · c42784e0cc95cfe0

harvested Assembly for Dreamer (graph method: Dreamer). 10 bricks; individually on a fixture: 9 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. Dreamer entry · level 0 · unverified · e6c80bdd218b3f8f
  2. ActionDecoder model · level 1 · ran · 032906ec0da4a020
  3. ConvDecoder model · level 1 · ran · c2fb17f9cc07745b
  4. ConvEncoder model · level 1 · ran · ea21fcd799d8f65e
  5. DenseDecoder model · level 1 · ran · 9647814e70d10581
  6. RSSM model · level 1 · ran · 6ed93a3bd0b35bbd
  7. ReplayBuffer helper · level 1 · ran · 9250128488be37e8
  8. preprocess_obs helper · level 1 · ran · our draft was wrong · b3d662dabfc89979
  9. SampleDist helper · level 1 · ran · f09ab92bd73f0a92
  10. TanhBijector helper · level 1 · ran · e441022cca867bcd

harvested Assembly for Dreamer (graph method: Dreamer). 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 7 siblings

  1. RecurrentStateSpaceModel entry · level 1 · ran · 06dafb6454d57ef2

harvested Assembly for Dreamer (graph method: Dreamer). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 7 siblings

  1. TransitionModel entry · level 0 · unverified · 28f50a7941b7cc60

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="1912.01603") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Continuous ControlReinforcement 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