Efficient Reinforcement Learning in Deterministic Systems with Value Function Generalization

Zheng Wen () and Benjamin Van Roy ()
Additional contact information
Zheng Wen: Adobe Research, San Jose, California 95110
Benjamin Van Roy: Stanford University, Stanford, California 94305

Mathematics of Operations Research, 2017, vol. 42, issue 3, 762-782

Abstract: We consider the problem of reinforcement learning over episodes of a finite-horizon deterministic system and as a solution propose optimistic constraint propagation ( OCP ), an algorithm designed to synthesize efficient exploration and value function generalization. We establish that when the true value function lies within a given hypothesis class, OCP selects optimal actions over all but at most D episodes, where D is the eluder dimension of the given hypothesis class. We establish further efficiency and asymptotic performance guarantees that apply even if the true value function does not lie in the given hypothesis class, for the special case where the hypothesis class is the span of prespecified indicator functions over disjoint sets. We also discuss the computational complexity of OCP and present computational results involving two illustrative examples.

Keywords: reinforcement learning; efficient exploration; value function generalization; approximate dynamic programming (search for similar items in EconPapers)
Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1287/moor.2016.0826 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:ormoor:v:42:y:2017:i:3:p:762-782

Access Statistics for this article

More articles in Mathematics of Operations Research from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().