Parameters tuning using RasID algorithm in Q value-based Dynamic Programming with Boltzmann Distribution

Author

Yu, Shanqing ; Mabu, Shingo ; Mainali, Manoj Kanta ; Hirasawa, Kotaro

Author_Institution

Grad. Sch. of Inf., Production & Syst., Waseda Univ., Fukuoka, Japan

fYear

2010

fDate

18-21 Aug. 2010

Firstpage

162

Lastpage

167

Abstract

In this paper, a new Temperature control strategy in the Q value-based Dynamic Programming with Boltzmann Distribution is proposed to improve the efficiency of Intelligent Transportation Systems. What´s more, Random Search with Intensification and Diversification (RasID) is used to optimize the parameters of Temperature control strategy. The simulation results shows that more suitable parameters could be obtained by using RasID algorithm and consequently alleviate congestion and improve the efficiency of the traffic system.

Keywords

automated highways; dynamic programming; statistical distributions; temperature control; tuning; Boltzmann distribution; Q value-based dynamic programming; RasID algorithm; intelligent transportation systems; parameter tuning; random search; temperature control strategy; Boltzmann distribution; Driver circuits; Dynamic programming; Heuristic algorithms; Roads; Temperature control; Vehicles; Boltzmann Distribution; Q value-based Dynamic Programming; RasID; Temperature Parameter;

fLanguage

English

Publisher

ieee

Conference_Titel

SICE Annual Conference 2010, Proceedings of

Conference_Location

Taipei

Print_ISBN

978-1-4244-7642-8

Type

conf

Filename

5602302