Physical Sciences and Mathematics Commons^™

Quantifying The Impact Of Non-Stationarity In Reinforcement Learning-Based Traffic Signal Control, Lucas N. Alegre, Ana L.C. Bazzan, Bruno C. Da Silva

Computer Science Department Faculty Publication Series

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 …