Publication Date
2021
Journal or Book Title
PeerJ Computer Science
Abstract
In reinforcement learning (RL), dealing with non-stationarity is a challenging issue. However, some domains such as traffic optimization are inherently non-stationary. Causes for and effects of this are manifold. In particular, when dealing with traffic signal controls, addressing non-stationarity is key since traffic conditions change over time and as a function of traffic control decisions taken in other parts of a network. In this paper we analyze the effects that different sources of non-stationarity have in a network of traffic signals, in which each signal is modeled as a learning agent. More precisely, we study both the effects of changing the context in which an agent learns (e.g., a change in flow rates experienced by it), as well as the effects of reducing agent observability of the true environment state. Partial observability may cause distinct states (in which distinct actions are optimal) to be seen as the same by the traffic signal agents. This, in turn, may lead to sub-optimal performance. We show that the lack of suitable sensors to provide a representative observation of the real state seems to affect the performance more drastically than the changes to the underlying traffic patterns.
ISSN
2376-5992
ORCID
Alegre, Lucas/0000-0001-5465-4390; Bazzan, Ana/0000-0002-2803-9607
DOI
https://doi.org/10.7717/peerj-cs.575
License
UMass Amherst Open Access Policy
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Funder
PeerJ Computer Science
Recommended Citation
Alegre, Lucas N.; Bazzan, Ana L.C.; and da Silva, Bruno C., "Quantifying the Impact of Non-Stationarity in Reinforcement Learning-Based Traffic Signal Control" (2021). PeerJ Computer Science. 1359.
https://doi.org/10.7717/peerj-cs.575
Included in
Artificial Intelligence and Robotics Commons, Databases and Information Systems Commons, Theory and Algorithms Commons