MétaCan
Menu
Back to cohort
Record W3136541527 · doi:10.1287/moor.2022.1331

Convergence of Finite Memory Q Learning for POMDPs and Near Optimality of Learned Policies Under Filter Stability

2022· article· en· W3136541527 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.
aboutThe title or abstract carries a Canadian signal from the geographic lexicon.

Bibliographic record

VenueMathematics of Operations Research · 2022
Typearticle
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsQueen's University
Fundersnot available
KeywordsMarkov decision processPartially observable Markov decision processConvergence (economics)Bellman equationMathematical optimizationMathematicsLimit (mathematics)Stability (learning theory)Filter (signal processing)Q-learningReinforcement learningOptimal controlErgodicityMarkov chainApplied mathematicsComputer scienceMarkov processArtificial intelligenceMachine learning

Abstract

fetched live from OpenAlex

In this paper, for partially observed Markov decision problems (POMDPs), we provide the convergence of a Q learning algorithm for control policies using a finite history of past observations and control actions, and consequentially, we establish near optimality of such limit Q functions under explicit filter stability conditions. We present explicit error bounds relating the approximation error to the length of the finite history window. We establish the convergence of such Q learning iterations under mild ergodicity assumptions on the state process during the exploration phase. We further show that the limit fixed point equation gives an optimal solution for an approximate belief Markov decision problem (MDP). We then provide bounds on the performance of the policy obtained using the limit Q values compared with the performance of the optimal policy for the POMDP, in which we also present explicit conditions using recent results on filter stability in controlled POMDPs. Whereas there exist many experimental results, (i) the rigorous asymptotic convergence (to an approximate MDP value function) for such finite memory Q learning algorithms and (ii) the near optimality with an explicit rate of convergence (in the memory size) under filter stability are results that are new to the literature to our knowledge. Funding: This research was supported in part by the Natural Sciences and Engineering Research Council (NSERC) of Canada.

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)0.003
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
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 score0.451
Threshold uncertainty score0.371

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
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 head0.196
GPT teacher head0.399
Teacher spread0.203 · 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