Pith. sign in

REVIEW 1 cited by

Sample Efficient Feature Selection for Factored MDPs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1703.03454 v1 pith:HCF7JPZ7 submitted 2017-03-09 cs.LG stat.ML

classification cs.LGstat.ML
keywords featuresin-degreefeaturenecessarysamplecomplexityfactoredlearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In reinforcement learning, the state of the real world is often represented by feature vectors. However, not all of the features may be pertinent for solving the current task. We propose Feature Selection Explore and Exploit (FS-EE), an algorithm that automatically selects the necessary features while learning a Factored Markov Decision Process, and prove that under mild assumptions, its sample complexity scales with the in-degree of the dynamics of just the necessary features, rather than the in-degree of all features. This can result in a much better sample complexity when the in-degree of the necessary features is smaller than the in-degree of all features.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Where to Intervene: Action Selection in Deep Reinforcement Learning

    stat.ML 2025-07 conditional novelty 5.0 of 10

    Knockoff sampling selects the minimal sufficient action set during online deep reinforcement learning with false discovery rate control.

Pith tools