Exploiting Structural Results in Approximate Dynamic Programming

Gnecco, Giorgio and Sanguineti, Marcello and Zoppoli, Riccardo Exploiting Structural Results in Approximate Dynamic Programming. In: EURO XXII, 8-11 July 2007, Prague, Czech Republic p. 159. (2007)

Full text not available from this repository.

Abstract

Efforts to cope with the curse of dimensionality in Dynamic Programming (DP) follow two main directions: i) problem simplification by simpler models and ii) use of smart approximators for the cost-to-go and/or policy functions. Here we focus on ii). We consider: a) structural properties of the cost-to-go and/or policy functions (to restrict approximation to certain function classes and to chose the approximators); b) suitable norms of the approximation error (to estimate how it propagates through stages). These ingredients can be combined to develop efficient approximate DP algorithms.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	22nd European Conference on operational research
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Research Area:	Computer Science and Applications
Depositing User:	Giorgio Gnecco
Date Deposited:	17 Sep 2013 13:12
Last Modified:	17 Sep 2013 13:12
URI:	http://eprints.imtlucca.it/id/eprint/1763

Available Versions of this Item

• Exploiting Structural Results in Approximate Dynamic Programming. (deposited 10 Sep 2013 12:08)
  • Exploiting Structural Results in Approximate Dynamic Programming. (deposited 17 Sep 2013 13:12) [Currently Displayed]
    • Exploiting Structural Results in Approximate Dynamic Programming. (deposited 17 Sep 2013 13:12)

Actions (login required)

Edit Item