MétaCan
Menu
Back to cohort
Record W4301342375 · doi:10.48550/arxiv.1503.02244

Asymptotic Optimality of Finite Approximations to Markov Decision\n Processes with Borel Spaces

2015· preprint· W4301342375 on OpenAlex

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

VenuearXiv (Cornell University) · 2015
Typepreprint
Language
FieldComputer Science
TopicMachine Learning and Algorithms
Canadian institutionsQueen's University
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsMarkov decision processMathematicsState spaceConvergence (economics)Applied mathematicsAction (physics)Mathematical optimizationMarkov chainSpace (punctuation)Class (philosophy)Markov processQ-learningFinite stateRate of convergenceAverage costReinforcement learningComputer scienceStatistics

Abstract

fetched live from OpenAlex

Calculating optimal policies is known to be computationally difficult for\nMarkov decision processes (MDPs) with Borel state and action spaces. This paper\nstudies finite-state approximations of discrete time Markov decision processes\nwith Borel state and action spaces, for both discounted and average costs\ncriteria. The stationary policies thus obtained are shown to approximate the\noptimal stationary policy with arbitrary precision under quite general\nconditions for discounted cost and more restrictive conditions for average\ncost. For compact-state MDPs, we obtain explicit rate of convergence bounds\nquantifying how the approximation improves as the size of the approximating\nfinite state space increases. Using information theoretic arguments, the order\noptimality of the obtained convergence rates is established for a large class\nof problems. We also show that, as a pre-processing step the action space can\nalso be finitely approximated with sufficiently large number points; thereby,\nwell known algorithms, such as value or policy iteration, Q-learning, etc., can\nbe used to calculate near optimal policies.\n

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)0.001
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
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 score0.690
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.004
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0030.003
Research integrity0.0000.001
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 head0.055
GPT teacher head0.210
Teacher spread0.155 · 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