Abstract
Reinforcement learning (RL) constitutes a promising solution for alleviating
the problem of traffic congestion. In particular, deep RL algorithms have been
shown to produce adaptive traffic signal controllers that outperform
conventional systems. However, in order to be reliable in highly dynamic urban
areas, such controllers need to be robust with the respect to a series of
exogenous sources of uncertainty. In this paper, we develop an open-source
callback-based framework for promoting the flexible evaluation of different
deep RL configurations under a traffic simulation environment. With this
framework, we investigate how deep RL-based adaptive traffic controllers
perform under different scenarios, namely under demand surges caused by special
events, capacity reductions from incidents and sensor failures. We extract
several key insights for the development of robust deep RL algorithms for
traffic control and propose concrete designs to mitigate the impact of the
considered exogenous uncertainties.
Original language | English |
---|---|
Title of host publication | Proceedings of the IEEE Intelligent Transportation Systems Conference (ITSC) 2019 |
Number of pages | 8 |
Publisher | IEEE |
Publication date | 2019 |
ISBN (Electronic) | 978-1-5386-7024-8 |
DOIs | |
Publication status | Published - 2019 |
Event | 22nd International IEEE Conference on Intelligent Transportation Systems - Conference Venue Cordis Hotel, Auckland, New Zealand Duration: 27 Oct 2019 → 30 Oct 2019 Conference number: 22 https://ieeexplore.ieee.org/xpl/conhome/8907344/proceeding |
Conference
Conference | 22nd International IEEE Conference on Intelligent Transportation Systems |
---|---|
Number | 22 |
Location | Conference Venue Cordis Hotel |
Country/Territory | New Zealand |
City | Auckland |
Period | 27/10/2019 → 30/10/2019 |
Internet address |