Skip to the main content

Other

Reinforcement Learning for Ramp Control: An Analysis of Learning Parameters

Chao Lu ; Beijing Institute of Technology
Jie Huang ; University of Leeds
Jianwei Gong ; Beijing Institute of Technology


Full text: english PDF 926 Kb

page 371-381

downloads: 632

cite


Abstract

Reinforcement Learning (RL) has been proposed to deal with ramp control problems under dynamic traffic conditions; however, there is a lack of sufficient research on the behaviour and impacts of different learning parameters. This paper describes a ramp control agent based on the RL mechanism and thoroughly analyzed the influence of three learning parameters; namely, learning rate, discount rate and action selection parameter on the algorithm performance. Two indices for the learning speed and convergence stability were used to measure the algorithm performance, based on which a series of simulation-based experiments were designed and conducted by using a macroscopic traffic flow model. Simulation results showed that, compared with the discount rate, the learning rate and action selection parameter made more remarkable impacts on the algorithm performance. Based on the analysis, some suggestions
about how to select suitable parameter values that can achieve a superior performance were provided.

Keywords

reinforcement learning; Q-learning; ramp control; agent; macroscopic traffic flow model; ent learning

Hrčak ID:

165546

URI

https://hrcak.srce.hr/165546

Publication date:

31.8.2016.

Visits: 1.308 *