MétaCan
Menu
Back to cohort
Record W4293370597 · doi:10.1109/lra.2022.3196132

Safe-Control-Gym: A Unified Benchmark Suite for Safe Learning-Based Control and Reinforcement Learning in Robotics

2022· article· en· W4293370597 on OpenAlexafffund
Zhaocong Yuan, Adam W. Hall, Siqi Zhou, Lukas Brunke, Melissa Greeff, Jacopo Panerati, Angela P. Schoellig

Bibliographic record

VenueIEEE Robotics and Automation Letters · 2022
Typearticle
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsDynamic Systems Analysis (Canada)Vector InstituteUniversity of Toronto
FundersNatural Sciences and Engineering Research Council of CanadaCanada Research Chairs
KeywordsReinforcement learningArtificial intelligenceComputer scienceSuiteBenchmark (surveying)Machine learning

Abstract

fetched live from OpenAlex

In recent years, both reinforcement learning and learning-based control—as well as the study of theirsafety, which is crucial for deployment in real-world robots—have gained significant traction. However, to adequately gauge the progress and applicability of new results, we need the tools to equitably compare the approaches proposed by the controls and reinforcement learning communities. Here, we propose a new open-source benchmark suite, calledsafe-control-gym, supporting both model-based and data-based control techniques. We provide implementations for three dynamic systems—the cart-pole, the 1D, and 2D quadrotor—and two control tasks—stabilization and trajectory tracking. We propose to extend OpenAI'sGymAPI—thede factostandard in reinforcement learning research—with(i)the ability to specify (and query) symbolic dynamics and(ii)constraints, and(iii)(repeatably) inject simulated disturbances in the control inputs, state measurements, and inertial properties. To demonstrate our proposal and in an attempt to bring research communities closer together, we show how to usesafe-control-gymto quantitatively compare the control performance, data efficiency, and safety of multiple approaches from the fields of traditional control, learning-based control, and reinforcement learning.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.011
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.016
Threshold uncertainty score0.032

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.011
Meta-epidemiology (narrow)0.0040.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0010.001
Scholarly communication0.0020.001
Open science0.0040.002
Research integrity0.0020.002
Insufficient payload (model declined to judge)0.0050.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.009
GPT teacher head0.221
Teacher spread0.212 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations47
Published2022
Admission routes2
Has abstractyes

Explore more

Same venueIEEE Robotics and Automation LettersSame topicReinforcement Learning in RoboticsFrench-language works237,207