Decentralized Learning for Traffic Signal Control

Prabuchandran, KJ and Hemanth, Kumar AN and Bhatnagar, Shalabh (2015) Decentralized Learning for Traffic Signal Control. In: 7th International Conference on Communication Systems and Networks, JAN 06-10, 2015, Bangalore, INDIA.

PDF 7th_Int_Con_Com_Sys_Net_2015.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

In this paper, we study the problem of obtaining the optimal order of the phase sequence 14] in a road network for efficiently managing the traffic flow. We model this problem as a Markov decision process (MDP). This problem is hard to solve when simultaneously considering all the junctions in the road network. So, we propose a decentralized multi-gent reinforcement learning (MARL) algorithm for solving this problem by considering each junction in the road network as a separate agent (controller). Each agent optimizes the order of the phase sequence using Q-learning with either E-greedy or VCB 3] based exploration strategies. The coordination between the junctions is achieved based on the cost feedback signal received from the neighbouring junctions. The learning algorithm for each agent updates the Q-factors using this feedback signal. We show through simulations over VISSIM that our algorithms perform significantly better than the standard fixed signal timing (FST), the saturation balancing (SAT) 14] and the round-robin multi-agent reinforcement learning algorithms 11] over two real road networks.

Item Type:	Conference Proceedings
Series.:	International Conference on Communication Systems and Networks
Additional Information:	Copy right for this article belongs to the IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	24 Aug 2016 10:22
Last Modified:	24 Aug 2016 10:22
URI:	http://eprints.iisc.ac.in/id/eprint/54539

Actions (login required)

View Item