MétaCan
Menu
Back to cohort
Record W4404047414 · doi:10.1137/24m1643736

Average Cost Optimality of Partially Observed MDPs: Contraction of Nonlinear Filters and Existence of Optimal Solutions and Approximations

2024· article· en· W4404047414 on OpenAlexafffund
Yunus Emre Demirci, Ali̇ Devran Kara, Serdar Yüksel

Bibliographic record

VenueSIAM Journal on Control and Optimization · 2024
Typearticle
Languageen
FieldMathematics
TopicAdvanced Optimization Algorithms Research
Canadian institutionsQueen's University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsMathematicsContraction (grammar)Nonlinear systemApproximations of πApplied mathematicsMathematical optimizationMathematical economics

Abstract

fetched live from OpenAlex

Abstract. The average cost optimality is known to be a challenging problem for partially observable stochastic control, with few results available beyond the finite state, action, and measurement setup, for which somewhat restrictive conditions are available. In this paper, we present explicit and easily testable conditions for the existence of solutions to the average cost optimality equation where the state space is compact. In particular, we present a novel contraction based analysis, which, to the best of our knowledge, is new to the literature, building on recent regularity results for nonlinear filters. Beyond establishing existence, we also present several implications of our analysis that also are new to the literature: (i) robustness to incorrect priors, (ii) near optimality of policies based on quantized approximations, (iii) near optimality of policies with finite memory, and (iv) convergence in Q-learning. In addition to our main theorem, each of these represents a novel contribution for average cost criteria.

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)0.006
metaresearch head score (Gemma)0.047
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: Methods · Consensus signal: Methods
Teacher disagreement score0.008
Threshold uncertainty score0.033

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.047
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0040.002
Bibliometrics0.0020.001
Science and technology studies0.0010.004
Scholarly communication0.0030.005
Open science0.0030.004
Research integrity0.0040.004
Insufficient payload (model declined to judge)0.0040.000

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 head0.072
GPT teacher head0.334
Teacher spread0.262 · 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
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

Citations5
Published2024
Admission routes2
Has abstractno

Explore more

Same venueSIAM Journal on Control and OptimizationSame topicAdvanced Optimization Algorithms ResearchFrench-language works237,207