MétaCan
Menu
Back to cohort
Record W197688093

An Architecture for Distinguishing between Predictors and Inhibitors in Reinforcement Learning

2013· article· en· W197688093 on OpenAlexaff
Patrick C. Connor, Thomas Trappenberg

Bibliographic record

VenuearXiv (Cornell University) · 2013
Typearticle
Languageen
FieldPsychology
TopicBehavioral and Psychological Studies
Canadian institutionsDalhousie University
Fundersnot available
KeywordsReinforcement learningReinforcementOutcome (game theory)Artificial intelligenceValence (chemistry)Value (mathematics)Machine learningComputer sciencePredictive valueStimulus (psychology)PsychologyMathematicsCognitive psychologySocial psychologyPhysics
DOInot available

Abstract

fetched live from OpenAlex

Reinforcement learning treats each input, feature, or stimulus as having a positive or negative reward value. Some stimuli, however, negate or inhibit the values of certain other predictors (excitors) when presented with them, but are otherwise neutral. We show that both linear and non-linear value-function approximators assign inhibitory features a strong value with the opposite valence of the predic-tor it inhibits (i.e., inhibitor =-excitor). In one circumstance, this gives a cor-rect prediction (i.e., excitor + inhibitor = neutral outcome). Importantly, however, value-function approximators incorrectly predict that when the inhibitor is pre-sented alone, a negative or oppositely valenced outcome will follow whereas the inhibitor alone is actually followed by a neutral outcome. Essentially, we show that having reward value as a direct predictive target can make inhibitors indistin-guishable from excitors that predict the oppositely valenced outcome. We show that this problem can be easily avoided if the reinforcement learning problem is broken into 1) a supervised learning module that predicts the positive appearance of primary reinforcements and 2) a reinforcement learning module which sums their agent-defined values. 1

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: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.006
Threshold uncertainty score0.485

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 integrity0.0000.000
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 head0.158
GPT teacher head0.244
Teacher spread0.085 · 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 designObservational
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
Published2013
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicBehavioral and Psychological StudiesFrench-language works237,207