MétaCan
Menu
Back to cohort

Behavior Replication of Cascaded Dynamic Systems Using Machine Learning

2023· article· en· W4391306300 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdaptive Dynamic Programming Control
Canadian institutionsUniversity of Ottawa
Fundersnot available
KeywordsComputer scienceReinforcement learningReference modelConvergence (economics)Process (computing)ReplicateSensitivity (control systems)System dynamicsReplication (statistics)Projection (relational algebra)Component (thermodynamics)Control theory (sociology)Artificial intelligenceControl (management)AlgorithmEngineeringMathematics

Abstract

fetched live from OpenAlex

This paper introduces an innovative data-driven approach for replicating behaviors in interconnected and heterogeneous dynamic systems. The core concept involves real-time control of dynamic systems to closely mimic reference-model trajectories using model-free techniques. Within this coupled framework, one component possesses complete information about reference-trajectories, although not necessarily their dynamics. In contrast, follower systems, with limited connectivity to reference-model trajectories, exclusively replicate the behavior of the primary process, which retains insight into model-reference dynamics. The adopted strategies are causal, integrating higher-order error dynamics to ensure precise tracking of reference-trajectories. Furthermore, these strategies incorporate variations in reference-model dynamics via a pseudo partial derivative, akin to sensitivity derivatives in model-reference adaptive strategies. To optimize the dynamic behavior of the follower process, the solution employs a reinforcement learning mechanism through adaptive critics. This mechanism approximates the optimal strategy and the associated value function. The actor and critic weights of the adaptive critic structure are tuned using a projection technique to ensure convergence of the adapted strategy. The validation of this solution is demonstrated on a dynamic system with delays, simulating an underwater vehicle scenario. The developed methodology is rigorously compared with another high-order model-free adaptive control approach. The presented approach showcases its capability to effectively replicate behaviors, resulting in improved tracking accuracy.

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.

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)0.001
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 score0.949
Threshold uncertainty score0.354

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.031
GPT teacher head0.300
Teacher spread0.269 · 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

Quick stats

Citations1
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicAdaptive Dynamic Programming ControlFrench-language works237,207