Naslov
A Comparison of Different State Representations for Reinforcement Learning Based Variable Speed Limit Control

Autori
Kušić, Krešimir ; Ivanjko, Edouard ; Gregurić, Martin

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of MED-2018 / - : Mediterranean Control Association, 2018, 266-271

ISBN
978-1-5090-4532-7

Skup
26th Mediterranean Conference on Control and Automation (MED 2018)

Mjesto i datum
Zadar, Hrvatska, 19.06.2018. - 22.06.2018

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Intelligent transportation systems, Intelligent control systems, Variable speed limit control, Reinforcement learning, Tile coding, Coarse coding, RBF

Sažetak
Variable Speed Limit Control (VSLC) is one control method for alleviating congestions on urban motorways. Machine learning techniques, like Reinforcement Learning (RL), are a promising alternative for setting up VSLC because an optimal control policy can be achieved with a smaller computational burden in comparison with optimal control approaches. A drawback is a large number of learning iterations and the problem of the exponential expansion of the state space dimension. This can be solved with function approximation techniques. Three different approaches for feature-based state representation in RL based VSLC are compared in this paper regarding the convergence of Total Time Spent. The microscopic traffic simulator VISSIM with a representative traffic model is used to evaluate the compared approaches. Results show that function approximation methods outperform RL based VSLC formulated with a lookup table by an average improvement of 10 %, where feature extraction methods (Coarse and Tile) coding showed slightly faster learning rate.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Tehnologija prometa i transport

POVEZANOST RADA