Publications
Detailed Information
Stochastic Subgradient Methods for Dynamic Programming in Continuous State and Action Spaces
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jang, Sunho | - |
dc.contributor.author | Yang, Insoon | - |
dc.date.accessioned | 2023-12-11T04:11:22Z | - |
dc.date.available | 2023-12-11T04:11:22Z | - |
dc.date.created | 2020-06-26 | - |
dc.date.issued | 2019-12 | - |
dc.identifier.citation | Proceedings of the IEEE Conference on Decision and Control, Vol.2019-December, pp.7287-7293 | - |
dc.identifier.issn | 0191-2216 | - |
dc.identifier.uri | https://hdl.handle.net/10371/198096 | - |
dc.description.abstract | © 2019 IEEE.In this paper, we propose a numerical method for dynamic programming in continuous state and action spaces. We first approximate the Bellman operator by using a convex optimization problem, which has many constraints. This convex program is then solved using stochastic subgradient descent. To avoid the full projection onto the high-dimensional feasible set, we develop a novel algorithm that samples, in a coordinated fashion, a mini-batch for a subgradient and another for projection. We show several salient properties of this algorithm, including convergence, and a reduction in the feasibility error and in the variance of the stochastic subgradient. | - |
dc.language | 영어 | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Stochastic Subgradient Methods for Dynamic Programming in Continuous State and Action Spaces | - |
dc.type | Article | - |
dc.citation.journaltitle | Proceedings of the IEEE Conference on Decision and Control | - |
dc.identifier.scopusid | 2-s2.0-85082447218 | - |
dc.citation.endpage | 7293 | - |
dc.citation.startpage | 7287 | - |
dc.citation.volume | 2019-December | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Yang, Insoon | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.