Papers › Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models

Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models

30 May 2018NeurIPS 2018 12arXiv:1805.12114archive 2025-07-28

Kurtland Chua, Roberto Calandra, Rowan Mcallister, Sergey Levine

Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. This is especially true with high-capacity parametric function approximators, such as deep networks. In this paper, we study how to bridge this gap, by employing uncertainty-aware dynamics models. We propose a new algorithm called probabilistic ensembles with trajectory sampling (PETS) that combines uncertainty-aware deep network dynamics models with sampling-based uncertainty propagation. Our comparison to state-of-the-art model-based and model-free deep RL algorithms shows that our approach matches the asymptotic performance of model-free algorithms on several challenging benchmark tasks, while requiring significantly fewer samples (e.g., 8 and 125 times fewer samples than Soft Actor Critic and Proximal Policy Optimization respectively on the half-cheetah task).

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

No sample from the archive's official repository (kchua/handful-of-trials) is linked to this paper; the 19 samples below come from 4 community repositories. Syntology harvested code from kchua/handful-of-trials for another paper.

kchua/handful-of-trials: Syntology's graph links these samples to Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers (arXiv:2006.13916; that paper's own run record: 21 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 5 honoured, 1 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method.

Syntology 19 code samples harvested from 4 repositories linked to this paper: 12 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 7 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): 19 samples from 4 repositories, 12 ran (7 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

kchua/handful-of-trials officialmentioned in papermentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers (arXiv:2006.13916; that paper's own run record: 21 ran (of which 4 constructed an object rather than computing a result; 14 with no instrument failure: 5 honoured, 1 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
ByMic/PETS mentioned on GitHubpytorchSyntology: 8 samples, 6 ran (4 instrument-failed) · 2 unverified report
Shunichi09/PythonLinearNonlinearControl mentioned on GitHubSyntology: not harvested report
facebookresearch/mbrl-lib mentioned on GitHubpytorchMITSyntology: not harvested report
github-jnauta/pytorch-pne mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles (arXiv:1612.01474; that paper's own run record: 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); nothing checks that they implement this paper's method. report
jingwu6/handful-of-trials-in-pytorch mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
natolambert/dynamicslearn mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
quanvuong/handful-of-trials-pytorch mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (1 instrument-failed) · 1 unverified report
sradicwebster/mbrl-lib mentioned on GitHubpytorchMITSyntology: 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

19 samples harvested: 12 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 7 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
6ran
7unverified

Licence: 17 of the 19 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 4 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.

ByMic/PETS community (archive-listed) 8 samples, 6 ran (4 instrument-failed) · 2 unverified
DNN utils/ensemble.py ran no licence file found · pointer only · 5ca4e528d445b8bb · report fixture: returned DNN · level recorded 2026-09-22
PNN utils/ensemble.py ran no licence file found · pointer only · a9c1528dfcc4652a · report fixture: returned PNN · level recorded 2026-09-22
normalize_deltas utils/ensemble.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 8a600321cfd91f4d · report fixture: signature deltas:Tensor/2/float, statistics:dict/0/? · returned Tensor · level recorded 2026-09-22
normalize_obs in 7 papers utils/ensemble.py ran; the contract check could not run (RAISES) no licence file found · pointer only · f1b4f8263ddf0967 · report fixture: signature obs:Tensor/2/float, statistics:dict/0/? · returned Tensor · level recorded 2026-09-22
silu in 15 papers
census: 5 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
utils/ensemble.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 35f8aeec75f44df1 · report fixture: signature x_input:Tensor/2/float · returned Tensor · level recorded 2026-09-22
unnormalize_deltas utils/ensemble.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 09253c3b2b54a147 · report fixture: signature normalized_deltas:Tensor/2/float, statistics:dict/0/? · returned Tensor · level recorded 2026-09-22
Ensemble in 6 papers utils/ensemble.py unverified no licence file found · pointer only · 1c0e747272c22445 · report
init_weights in 109 papers utils/ensemble.py unverified no licence file found · pointer only · 48fe26920f96d27b · report
jingwu6/handful-of-trials-in-pytorch community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
BNN modeling/models/BNN.py ran no licence file found · pointer only · f13fc61d4b56b01e · report fixture: signature inputs:Tensor/2/float, ret_logvar:bool/0/bool · returned tuple · level recorded 2026-09-24
get_affine_params modeling/models/BNN.py unverified no licence file found · pointer only · 139faffd313f0eb3 · report
truncated_normal in 12 papers modeling/models/BNN.py unverified no licence file found · pointer only · 24b8d2393ffaa19e · report
natolambert/dynamicslearn community (archive-listed) 2 samples, 0 ran · 2 unverified
EnsembleNN learn/models/model_ensemble_nn.py unverified MIT (permissive) · d45086d0d8ac50af · report
GeneralNN learn/models/model_ensemble_nn.py unverified MIT (permissive) · d696ce3649bc23c0 · report
quanvuong/handful-of-trials-pytorch community (archive-listed) 6 samples, 5 ran (1 instrument-failed) · 1 unverified
CEMOptimizer MPC.py ran no licence file found · pointer only · eeb421621d540f5f · report fixture: returned CEMOptimizer · level recorded 2026-09-22
Controller MPC.py ran no licence file found · pointer only · e4ea9ddc4d8483c2 · report fixture: returned Controller · level recorded 2026-09-22
Optimizer in 18 papers MPC.py ran no licence file found · pointer only · 5938fc919ec8c9ab · report fixture: returned Optimizer · level recorded 2026-09-22
get_required_argument in 7 papers MPC.py ran · our draft was wrong no licence file found · pointer only · 4eb5226056a1f70f · report fixture: signature dotmap:dict/0/?, key:str/0/str, message:str/0/str, default:NoneType/0/? · returned str · level recorded 2026-09-22
shuffle_rows in 6 papers MPC.py ran · honoured contract fingerprinted no licence file found · pointer only · 14a3c589a22e7e32 · report fixture: signature arr:ndarray/2/float · returned ndarray · level recorded 2026-09-22
MPC MPC.py unverified no licence file found · pointer only · 88a7bccc5d349061 · 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.

4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

4 sibling assemblies for Probabilistic Ensembles with Trajectory Sampling (PETS) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Probabilistic Ensembles with Trajectory Sampling (PETS) (graph method: Probabilistic Ensembles with Trajectory Sampling (PETS)). 6 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. MPC entry · level 0 · unverified · 88a7bccc5d349061
  2. CEMOptimizer scheduler · level 1 · ran · eeb421621d540f5f
  3. Controller helper · level 1 · ran · e4ea9ddc4d8483c2
  4. get_required_argument helper · level 1 · ran · our draft was wrong · 4eb5226056a1f70f
  5. shuffle_rows helper · level 1 · ran · honoured contract · 14a3c589a22e7e32
  6. Optimizer helper · level 1 · ran · 5938fc919ec8c9ab

harvested Assembly for Probabilistic Ensembles with Trajectory Sampling (PETS) (graph method: Probabilistic Ensembles with Trajectory Sampling (PETS)). 4 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. BNN entry · level 1 · ran · f13fc61d4b56b01e
  2. get_affine_params helper · level 0 · unverified · 139faffd313f0eb3
  3. swish helper · level 2 · ran · our draft was wrong · 0f786c407fb1ee4c
  4. truncated_normal helper · level 0 · unverified · 24b8d2393ffaa19e

harvested Assembly for Probabilistic Ensembles with Trajectory Sampling (PETS) (graph method: Probabilistic Ensembles with Trajectory Sampling (PETS)). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. EnsembleNN entry · level 0 · unverified · d45086d0d8ac50af
  2. GeneralNN model · level 0 · unverified · d696ce3649bc23c0

harvested Assembly for Probabilistic Ensembles with Trajectory Sampling (PETS) (graph method: Probabilistic Ensembles with Trajectory Sampling (PETS)). 8 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. Ensemble entry · level 0 · unverified · 1c0e747272c22445
  2. DNN model · level 1 · ran · 5ca4e528d445b8bb
  3. PNN model · level 1 · ran · a9c1528dfcc4652a
  4. init_weights helper · level 0 · unverified · 48fe26920f96d27b
  5. normalize_deltas helper · level 1 · ran; the contract check could not run (RAISES) · 8a600321cfd91f4d
  6. normalize_obs helper · level 1 · ran; the contract check could not run (RAISES) · f1b4f8263ddf0967
  7. silu helper · level 1 · ran · our draft was wrong · 35f8aeec75f44df1
  8. unnormalize_deltas helper · level 1 · ran; the contract check could not run (RAISES) · 09253c3b2b54a147

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="1805.12114") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Deep Reinforcement LearningModel-based Reinforcement LearningReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamDense ConnectionsExperience ReplayReLUSoft Actor Critic

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