MétaCan
Menu
Back to cohort
Record W3185807839 · doi:10.1109/tie.2021.3099234

Reinforcement Learning With Constrained Uncertain Reward Function Through Particle Filtering

2021· article· en· W3185807839 on OpenAlexafffund
Oguzhan Dogru, Ranjith Chiplunkar, Biao Huang

Bibliographic record

VenueIEEE Transactions on Industrial Electronics · 2021
Typearticle
Languageen
FieldEngineering
TopicFault Detection and Control Systems
Canadian institutionsUniversity of Alberta
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsReinforcement learningNoise (video)Probabilistic logicProcess (computing)Computer scienceFilter (signal processing)Particle filterArtificial intelligenceFunction (biology)ReinforcementQuality (philosophy)Machine learningEngineeringComputer vision

Abstract

fetched live from OpenAlex

Advancements in computational sciences have stimulated the use of an abundant amount of data in control and monitoring. Recent studies have reemphasized that the performance of the data-driven control significantly depends on the data quality. This quality is affected by uncertainties such as process and measurement noises. This study addresses a type of noise commonly seen in industry and shows how it degrades the performance of a deep reinforcement learning (RL) agent. Then, a novel filter is proposed to reduce the effect of this noise when it causes skewed probabilistic distributions in the reward functions. We demonstrate that the RL policy can be improved by using a constrained filter with a combination of the optimal filtering and RL concepts. The proposed algorithm is applied to a pilot-scale separation process that resembles an industrial separation vessel. The experimental results demonstrate that the proposed algorithm can improve the process operation efficiency.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.924
Threshold uncertainty score0.845

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.023
GPT teacher head0.223
Teacher spread0.199 · 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 teacher head, 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

Citations13
Published2021
Admission routes2
Has abstractyes

Explore more

Same venueIEEE Transactions on Industrial ElectronicsSame topicFault Detection and Control SystemsFrench-language works237,207