MétaCan
Menu
Back to cohort
Record W3175841314

Nearly Minimax Optimal Reinforcement Learning for Linear Mixture MDPs

2021· article· en· W3175841314 on OpenAlexaff
Dongruo Zhou, Quanquan Gu, Csaba Szepesvári

Bibliographic record

VenueConference on Learning Theory · 2021
Typearticle
Languageen
FieldDecision Sciences
TopicAdvanced Bandit Algorithms Research
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsReinforcement learningMarkov decision processMathematicsMinimaxLogarithmEstimatorBounded functionCombinatoricsDiscrete mathematicsRegretMathematical optimizationMarkov processComputer scienceArtificial intelligenceStatistics
DOInot available

Abstract

fetched live from OpenAlex

We study reinforcement learning (RL) with linear function approximation where the underlying transition probability kernel of the Markov decision process (MDP) is a linear mixture model (Jia et al., 2020; Ayoub et al., 2020; Zhou et al., 2020) and the learning agent has access to either an integration or a sampling oracle of the individual basis kernels. For the fixed-horizon episodic setting with inhomogeneous transition kernels, we propose a new, computationally efficient algorithm that uses the basis kernels to approximate value functions. We show that the new algorithm, which we call ${\text{UCRL-VTR}^{+}}$, attains an $\tilde O(dH\sqrt{T})$ regret where $d$ is the number of basis kernels, $H$ is the length of the episode and $T$ is the number of interactions with the MDP. We also prove a matching lower bound $\Omega(dH\sqrt{T})$ for this setting, which shows that ${\text{UCRL-VTR}^{+}}$ is minimax optimal up to logarithmic factors. At the core of our results are (1) a weighted least squares estimator for the unknown transitional probability; and (2) a new Bernstein-type concentration inequality for self-normalized vector-valued martingales with bounded increments. Together, these new tools enable tight control of the Bellman error and lead to a nearly minimax regret. To the best of our knowledge, this is the first computationally efficient, nearly minimax optimal algorithm for RL with linear function approximation.

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)0.004
metaresearch head score (Gemma)0.019
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 score0.007
Threshold uncertainty score0.023

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.019
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0030.001
Bibliometrics0.0010.001
Science and technology studies0.0010.003
Scholarly communication0.0020.003
Open science0.0020.003
Research integrity0.0020.004
Insufficient payload (model declined to judge)0.0030.000

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 head0.128
GPT teacher head0.424
Teacher spread0.296 · 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

Citations0
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueConference on Learning TheorySame topicAdvanced Bandit Algorithms ResearchFrench-language works237,207