Papers › Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

29 Jun 2022ICLR 2022 4arXiv:2206.14697archive 2025-07-28

Vaisakh Shaj, Dieter Buchler, Rohit Sonker, Philipp Becker, Gerhard Neumann

Recurrent State-space models (RSSMs) are highly expressive models for learning patterns in time series data and system identification. However, these models assume that the dynamics are fixed and unchanging, which is rarely the case in real-world scenarios. Many control applications often exhibit tasks with similar but not identical dynamics which can be modeled as a latent variable. We introduce the Hidden Parameter Recurrent State Space Models (HiP-RSSMs), a framework that parametrizes a family of related dynamical systems with a low-dimensional set of latent factors. We present a simple and effective way of learning and performing inference over this Gaussian graphical model that avoids approximations like variational inference. We show that HiP-RSSMs outperforms RSSMs and competing multi-task models on several challenging robotic benchmarks both on real-world systems and simulations.

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.

Syntology holds a reference implementation of Hidden Parameter Recurrent State Space Models (HiP-RSSMs), generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Hidden Parameter Recurrent State Space Models (HiP-RSSMs)') (how to connect); the free check have('2206.14697') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 22 code samples harvested from 1 repository linked to this paper: 14 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 14 ran (9 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.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ALRhub/HiP-RSSM officialpytorchSyntology: 22 samples, 14 ran (5 instrument-failed) · 8 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.

Code Syntology ran Syntology

22 samples harvested: 14 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 8 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
1ran · our draft was wrong
4ran; the contract check could not run
8ran
8unverified

Licence: 22 of the 22 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 ALRhub/HiP-RSSM. “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 4 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.

ALRhub/HiP-RSSM official repository 22 samples, 14 ran (5 instrument-failed) · 8 unverified
Coefficient metaWorldModels/hiprssm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 4822c817a021c778 · report fixture: returned Coefficient · level recorded 2026-09-22
Control metaWorldModels/hiprssm.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · d605bc945f5f9153 · report fixture: returned Control · level recorded 2026-09-22
ProcessNoise metaWorldModels/hiprssm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0203a57e00b7f01d · report fixture: returned ProcessNoise · level recorded 2026-09-22
SetEncoder metaWorldModels/hiprssm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2959a5295c2d022e · report fixture: returned SetEncoder · level recorded 2026-09-22
TaskNetMu metaWorldModels/hiprssm.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 91a2f84bc249662b · report fixture: returned TaskNetMu · level recorded 2026-09-22
TaskNetVar metaWorldModels/hiprssm.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 3c1e2f8def35132b · report fixture: returned TaskNetVar · level recorded 2026-09-22
TimeDistributed in 5 papers metaWorldModels/hiprssm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3347e66b80c710a0 · report fixture: returned TimeDistributed · level recorded 2026-09-22
Update metaWorldModels/hiprssm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5bd2c4165a25b1b5 · report fixture: returned Update · level recorded 2026-09-22
bmv metaWorldModels/hiprssm.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 4a9426681a42c34d · report fixture: signature mat:Tensor/3/float, vec:Tensor/2/float · returned Tensor · level recorded 2026-09-22
cov_locally_linear_transform metaWorldModels/hiprssm.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 9acad9d5d7634c64 · report fixture: signature tm:list/1/Tensor, covar:list/1/Tensor, process_covar:Tensor/2/float · returned list · level recorded 2026-09-22
dadat metaWorldModels/hiprssm.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 2bbcb436e1373798 · report fixture: signature a:Tensor/3/float, diag_mat:Tensor/2/float · returned Tensor · level recorded 2026-09-22
dadbt metaWorldModels/hiprssm.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · d5e169f67e3d185d · report fixture: signature a:Tensor/3/float, diag_mat:Tensor/2/float, b:Tensor/3/float · returned Tensor · level recorded 2026-09-22
elup1_inv metaWorldModels/hiprssm.py ran · honoured contract no licence file found · pointer only · 4e9c78de883a6c5d · report fixture: signature x:Tensor/0/float · returned Tensor · level recorded 2026-09-22
gaussian_locally_linear_transform metaWorldModels/hiprssm.py ran · our draft was wrong no licence file found · pointer only · c981bde6b0241080 · report fixture: signature tm:list/1/Tensor, mean:Tensor/2/float, covar:list/1/Tensor, control_factor:Tensor/2/float, process_covar:Tensor/2/float · returned tuple · level recorded 2026-09-22
AcPredict metaWorldModels/hiprssm.py unverified no licence file found · pointer only · a94397b32d604b6f · report
AcRKNContextLayer metaWorldModels/hiprssm.py unverified no licence file found · pointer only · 1daad337f6267d37 · report
Encoder in 278 papers metaWorldModels/hiprssm.py unverified no licence file found · pointer only · 1a9e3fa5cdd50673 · report
HipRSSM metaWorldModels/hiprssm.py unverified no licence file found · pointer only · 630ff86cdf3971db · report
SplitDiagGaussianDecoder metaWorldModels/hiprssm.py unverified no licence file found · pointer only · e810af53700c6ee0 · report
acrknContextualDecoder metaWorldModels/hiprssm.py unverified no licence file found · pointer only · ea3f94550cabf415 · report
cov_linear_transform metaWorldModels/hiprssm.py unverified no licence file found · pointer only · f7505a07a5dde12f · report
gaussian_linear_transform metaWorldModels/hiprssm.py unverified no licence file found · pointer only · a06192c0b4a86930 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for Hidden Parameter Recurrent State Space Models (HiP-RSSMs) (graph method: Hidden Parameter Recurrent State Space Models (HiP-RSSMs)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. kalman_observation_update entry · level 2 · ran · 835f237560dee78d33f1929e69e2c706182a33ab127998a76a9502e7e74c59d9

harvested Assembly for Hidden Parameter Recurrent State Space Models (HiP-RSSMs) (graph method: Hidden Parameter Recurrent State Space Models (HiP-RSSMs)). 23 bricks; individually on a fixture: 15 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. HipRSSM entry · level 0 · unverified · 630ff86cdf3971db
  2. SetEncoder helper · level 1 · ran · 2959a5295c2d022e
  3. acrknContextualDecoder model · level 0 · unverified · ea3f94550cabf415
  4. elup1 helper · level 1 · ran · honoured contract · 6137076d036ffe8f
  5. AcRKNContextLayer model · level 0 · unverified · 1daad337f6267d37
  6. Encoder helper · level 0 · unverified · 1a9e3fa5cdd50673
  7. SplitDiagGaussianDecoder helper · level 0 · unverified · e810af53700c6ee0
  8. TimeDistributed helper · level 1 · ran · 3347e66b80c710a0
  9. elup1_inv helper · level 1 · ran · honoured contract · 4e9c78de883a6c5d
  10. AcPredict helper · level 0 · unverified · a94397b32d604b6f
  11. Update helper · level 1 · ran · 5bd2c4165a25b1b5
  12. Coefficient helper · level 1 · ran · 4822c817a021c778
  13. Control helper · level 1 · ran · d605bc945f5f9153
  14. ProcessNoise helper · level 1 · ran · 0203a57e00b7f01d
  15. TaskNetMu helper · level 1 · ran · 91a2f84bc249662b
  16. TaskNetVar helper · level 1 · ran · 3c1e2f8def35132b
  17. gaussian_linear_transform helper · level 0 · unverified · a06192c0b4a86930
  18. gaussian_locally_linear_transform helper · level 1 · ran · our draft was wrong · c981bde6b0241080
  19. cov_linear_transform helper · level 0 · unverified · f7505a07a5dde12f
  20. bmv helper · level 1 · ran; the contract check could not run (RAISES) · 4a9426681a42c34d
  21. cov_locally_linear_transform helper · level 1 · ran; the contract check could not run (RAISES) · 9acad9d5d7634c64
  22. dadat helper · level 1 · ran; the contract check could not run (RAISES) · 2bbcb436e1373798
  23. dadbt helper · level 1 · ran; the contract check could not run (RAISES) · d5e169f67e3d185d

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="2206.14697") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

State Space ModelsTime SeriesTime Series AnalysisVariational Inference

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