Papers › Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model

1 Jul 2019NeurIPS 2020 12arXiv:1907.00953archive 2025-07-28

Alex X. Lee, Anusha Nagabandi, Pieter Abbeel, Sergey Levine

Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must now solve two problems: representation learning and task learning. In this work, we tackle these two problems separately, by explicitly learning latent representations that can accelerate reinforcement learning from images. We propose the stochastic latent actor-critic (SLAC) algorithm: a sample-efficient and high-performing RL algorithm for learning policies for complex continuous control tasks directly from high-dimensional image inputs. SLAC provides a novel and principled approach for unifying stochastic sequential models and RL into a single method, by learning a compact latent representation and then performing RL in the model's learned latent space. Our experimental evaluation demonstrates that our method outperforms both model-free and model-based alternatives in terms of final performance and sample efficiency, on a range of difficult image-based control tasks. Our code and videos of our results are available at our website.

PaperPDFConference PDFCodeCode 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 11 code samples harvested from 4 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 4 repositories, 10 ran (7 with no instrument failure; 3 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 1 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.

alexlee-gk/slac mentioned on GitHubtfSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
fgitmichael/SVAEfromSLAC mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
fgitmichael/TestModeDisentangling mentioned on GitHubpytorchMITSyntology: not harvested report
ku2482/rljax mentioned on GitHubjaxMITSyntology: not harvested report
ku2482/slac.pytorch mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
lava-lab/safe-slac mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
safe-slac/safe-slac mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation (arXiv:2210.01801; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
toshikwa/slac.pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
yusukeurakami/slac-playground mentioned on GitHubpytorchSyntology: 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

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 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.

2ran · our draft was wrong
1ran; the contract check could not run
7ran
1unverified

Licence: 1 of the 11 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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.

alexlee-gk/slac community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
get_train_eval_dir slac/agents/slac/examples/v1/train_eval.py ran · our draft was wrong MIT (permissive) · 5f66e761fbab47db · report fixture: signature root_dir:str/0/str, universe:str/0/str, env_name:str/0/str, domain_name:str/0/str, task_name:str/0/str, experiment_name:str/0/str · returned str · level recorded 2026-09-22
pad_and_concatenate_videos slac/agents/slac/examples/v1/train_eval.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed MIT (permissive) · 445310dc406996c6 · report fixture: signature videos:list/1/list · returned list · level recorded 2026-09-22
fgitmichael/SVAEfromSLAC community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
calc_kl_divergence code/utils.py ran MIT (permissive) · f30217e64bc444de · report fixture: signature p_list:list/1/Normal, q_list:list/1/Normal · returned Tensor · level recorded 2026-09-24
create_feature_actions code/utils.py ran fingerprinted MIT (permissive) · 6ef32f14e01dbc6c · report fixture: signature features_seq:Tensor/3/float, actions_seq:Tensor/3/float · returned tuple · level recorded 2026-09-24
create_linear_network code/network/base.py ran MIT (permissive) · cbde590787975d24 · report fixture: signature input_dim:int/0/int, output_dim:int/0/int, hidden_units:list/1/int, hidden_activation:callable/0/?, output_activation:callable/0/?, initializer:callable/0/? · returned Sequential · level recorded 2026-09-24
ku2482/slac.pytorch community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
build_mlp in 74 papers slac/utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · c511268a73d82fc6 · report fixture: returned Sequential · level recorded 2026-09-22
calculate_gaussian_log_prob slac/utils.py ran fingerprinted MIT (permissive) · 749c89653f96f209 · report fixture: signature log_std:Tensor/2/float, noise:Tensor/2/float · returned Tensor · level recorded 2026-09-24
create_feature_actions slac/utils.py ran fingerprinted MIT (permissive) · c17d4065283d4027 · report fixture: signature feature_:Tensor/3/float, action_:Tensor/3/float · returned tuple · level recorded 2026-09-25
lava-lab/safe-slac community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
build_mlp in 74 papers slac/utils.py ran MIT (permissive) · bcd2f30df5201848 · report fixture: signature input_dim:int/0/int, output_dim:int/0/int, hidden_units:list/1/int, hidden_activation:callable/0/?, output_activation:NoneType/0/? · returned Sequential · level recorded 2026-09-25
sample_reproduction slac/utils.py ran MIT (permissive) · f958d15bc44a28f7 · report fixture: signature latent_model:callable/0/?, device:str/0/str, state:list/1/list, action:list/1/list · returned ndarray · level recorded 2026-09-25
make_safety slac/env.py unverified MIT (permissive) · c63d0b541a34fef9 · report

Tasks

Continuous ControlDeep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)Representation Learningcontinuous-controlreinforcement-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