MétaCan
Menu
Back to cohort
Record W4389192605 · doi:10.22215/etd/2023-15720

Multi-Agent Cooperative Fuzzy Reinforcement Learning

2023· dissertation· en· W4389192605 on OpenAlexaff
Rachel Haighton

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldEconomics, Econometrics and Finance
TopicComplex Systems and Time Series Analysis
Canadian institutionsCarleton University
Fundersnot available
KeywordsReinforcement learningInterpretabilityArtificial intelligenceComputer scienceFuzzy logicHyperparameterMachine learningMulti-agent system

Abstract

fetched live from OpenAlex

This thesis explores multi-agent cooperative reinforcement learning using fuzzy systems.Two main problems are studied: multi-agent systems learning altruism, and cooperative agents in non-stationary environments.Fuzzy inference systems are used as the main function approximators due to their inherent transparency and interpretability.Altruism within multi-agent systems is displayed when an agent can choose actions that are beneficial to the group without necessarily being beneficial to itself.To learn this behavior, a genetic algorithm is used to select reinforcement learning hyperparameters.The hyperparameters that are selected to tune are: the discount factor, a reward function weight, and standard deviation of noise applied during learning.These parameters are largely linked in the game being played.The second problem studied is one in which cooperative multi-agent systems learn in non-stationary environments.A hierarchical reinforcement learning structure is proposed as a finite time horizon model-free solution.The temporal difference error acts as an indicator of environment change.

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)0.001
metaresearch head score (Gemma)0.003
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 score0.004
Threshold uncertainty score0.008

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.000
Science and technology studies0.0000.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.000

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 head0.048
GPT teacher head0.257
Teacher spread0.210 · 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

Citations0
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicComplex Systems and Time Series AnalysisFrench-language works237,207