MétaCan
Menu
Back to cohort
Record W4403935894 · doi:10.1145/3652620.3676878

Towards Model Repair by Human Opinion--Guided Reinforcement Learning

2024· article· en· W4403935894 on OpenAlexaff
Kyanna Dagenais

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsMcMaster University
Fundersnot available
KeywordsReinforcement learningComputer scienceReinforcementArtificial intelligenceHuman–computer interactionEngineeringStructural engineering

Abstract

fetched live from OpenAlex

Model repair often entails long sequences of model transformations. Finding the correct model repair sequence is challenging, and its complexity increases with the number of model transformations involved in the repair sequence. In realistic, longitudinally extensive modelling settings, the same model repair scenarios might be encountered repeatedly, providing an excellent opportunity to learn the most appropriate repair actions through reinforcement learning (RL). While such ideas have been explored before, the efficiency of RL-based methods in long repair sequences is still an open challenge. In this paper, we propose a method to improve learning performance by human opinions---cognitive constructs that are subject to uncertainty, but also emerge earlier than hard evidence. Our findings indicate that opinion-based guidance significantly improves the learning performance, even with moderately uncertain human opinions. To counter the uncertainty of individual human advisors, our method allows for collaborative guidance by experts of various expertise and skill levels.

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)0.001
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: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.784
Threshold uncertainty score0.872

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.001
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 head0.038
GPT teacher head0.312
Teacher spread0.274 · 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
GenreMethods

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

Citations2
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicReinforcement Learning in RoboticsFrench-language works237,207