Metadata only
Date
2017-07Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
In this paper, we propose a novel formulation for encoding state constraints into the Linear Programming approach to Approximate Dynamic Programming via the use of penalty functions. To maintain tractability of the resulting optimization problem that needs to be solved, we suggest a penalty function that is constructed as a point-wise maximum taken over a family of low-order polynomials. Once the penalty functions are designed, no additional approximations are introduced by the proposed formulation. The effectiveness and numerical stability of the formulation is demonstrated through examples Show more
Publication status
publishedExternal links
Book title
20th IFAC World Congress. ProceedingsJournal / series
IFAC-PapersOnLineVolume
Pages / Article No.
Publisher
ElsevierEvent
Subject
Stochastic optimal control problems; Approximate dynamic programming; Soft constraintsOrganisational unit
03751 - Lygeros, John / Lygeros, John
More
Show all metadata
ETH Bibliography
yes
Altmetrics