MétaCan
Menu
Back to cohort

The Non-Walking Triangle Optimization Representation: Enabling Monte Carlo Tree Search-like Methods for Real Parameter Optimization Problems

2021· article· en· W4206945128 on OpenAlex
Rachel Brown, Daniel Ashlock

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.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venue2021 IEEE Symposium Series on Computational Intelligence (SSCI) · 2021
Typearticle
Languageen
FieldComputer Science
TopicArtificial Intelligence in Games
Canadian institutionsUniversity of Guelph
FundersUniversity of Guelph
KeywordsMonte Carlo methodAlgorithmMathematicsTree (set theory)Mathematical optimizationComputer scienceOptimization problemRepresentation (politics)StatisticsCombinatorics

Abstract

fetched live from OpenAlex

Real parameter estimation is typically performed by an algorithm that operates directly on vectors of real parameters. This study presents an extension of a representation for real parameter optimization that is discrete and based on the iterated partition of simplices, known as the Walking Triangle Representation (WTR), and pairs it with Monte Carlo Tree Search (MCTS)-like algorithms. The number of moves allowed to the WTR is reduced to only its centering move, where a vertex of the simplex is replaced by its center of mass. This representation converts a real parameter optimization to a discrete form, which can then be paired with MCTS-like algorithms. The tree structure of MCTS allows one to keep track of and exploit information from previous attempts (tree extensions) when choosing the next set of moves to try. Six real parameter optimization problems were used to test the algorithm. Four parameters in the algorithm were studied, including: minimum gene length, maximum gene length, number of tree extensions, and probability of exploration (chance). The algorithm regularly performed consistently well, even with a low number of fitness evaluations (typical number of fitness evaluations is up to 3750 per run). This paper focuses on the ability of the Non-Walking Triangle Representation to convert real parameter optimization problems into discrete representations. This concept is demonstrated through the evaluation of the Non-Walking Triangle Monte Carlo Tree Search (MCNon-Walk) algorithm's ability to find optima in a variety of real parameter optimization problems, using differential evolution as a baseline for comparison.

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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.091
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.002
Science and technology studies0.0010.000
Scholarly communication0.0020.002
Open science0.0010.000
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 head0.060
GPT teacher head0.359
Teacher spread0.299 · 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