Structural results for cooperative decentralized control models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Structural results for cooperative decentralized control models

Abstract

The intractability in cooperative, decentralized con- trol models is mainly due to prohibitive memory requirements in both optimal policies and value functions. The complexity analysis has emerged as the standard method to estimating the memory needed for solving a given computational problem, but complexity results may be somewhat limited. This paper introduces a general methodology— structural analysis—for the design of optimality- preserving concise policies and value functions, which will eventually lead to the development of efficient theory and algorithms. For the first time, we show that memory requirements for policies and value functions may be asymmetric, resulting in co- operative, decentralized control models with expo- nential reductions in memory requirements.
No file

Dates and versions

hal-01188481 , version 1 (30-08-2015)

Identifiers

  • HAL Id : hal-01188481 , version 1

Cite

Jilles Steeve Dibangoye, Olivier Buffet, Olivier Simonin. Structural results for cooperative decentralized control models. Proceedings of the twenty-fourth international joint conference on artificial intelligence, IJCAI 2015, Jul 2015, Buenos Aires, Argentina. ⟨hal-01188481⟩
135 View
0 Download

Share

Gmail Facebook X LinkedIn More