MétaCan
Menu
Back to cohort
Record W191658262

{Toward Minimax Off-policy Value Estimation}

2015· article· en· W191658262 on OpenAlexaff
Lihong Li, Rémi Munos, Csaba Szepesvári

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldDecision Sciences
TopicAdvanced Bandit Algorithms Research
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsEstimatorMinimaxMarkov decision processMultiplicative functionMathematical optimizationOracleComputer scienceTime horizonLimit (mathematics)Sample size determinationUpper and lower boundsMathematicsSample (material)Value (mathematics)Markov processStatistics
DOInot available

Abstract

fetched live from OpenAlex

This paper studies the off-policy evaluation prob-lem, where one aims to estimate the value of a target policy based on a sample of observations collected by another policy. We first consider the single-state, or multi-armed bandit case, estab-lish a finite-time minimax risk lower bound, and analyze the risk of three standard estimators. For the so-called regression estimator, we show that while it is asymptotically optimal, for small sam-ple sizes it may perform suboptimally compared to an ideal oracle up to a multiplicative factor that depends on the number of actions. We also show that the other two popular estimators can be ar-bitrarily worse than the optimal, even in the limit of infinitely many data points. The performance of the estimators are studied in synthetic and real problems; illustrating the methods strengths and weaknesses. We also discuss the implications of these results for off-policy evaluation problems in contextual bandits and fixed-horizon Markov decision processes. 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 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)0.014
metaresearch head score (Gemma)0.064
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.014
Threshold uncertainty score0.074

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0140.064
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0040.001
Bibliometrics0.0020.001
Science and technology studies0.0010.004
Scholarly communication0.0030.005
Open science0.0020.003
Research integrity0.0030.005
Insufficient payload (model declined to judge)0.0040.001

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 head0.365
GPT teacher head0.525
Teacher spread0.160 · 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 designTheoretical or conceptual
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

Citations62
Published2015
Admission routes1
Has abstractyes

Explore more

Same topicAdvanced Bandit Algorithms ResearchFrench-language works237,207