Intelligent Transportation Aiding Urban Sustainability: An Empirical Analysis with Reinforcement and Deep Learning

With the acceleration of global urbanization, issues such as traffic congestion, energy consumption, and environmental pollution have become increasingly prominent, severely constraining urban sustainable development. Intelligent Transportation Systems (ITS), by introducing advanced technological means, hold promise for alleviating these problems. However, how to quantify the impact of ITS on urban sustainable development and optimize ITS performance requires in-depth research. This paper constructs an ITS optimization model integrating Multi-Agent Deep Reinforcement Learning, exploring the impact mechanisms of ITS on urban sustainable development from theoretical and empirical perspectives. We introduce complex metrics, including traffic flow, environmental indicators, and socio-economic data to comprehensively validate and analyze the model. The results show that the optimized ITS significantly improves traffic efficiency, reduces energy consumption and carbon emissions, and promotes urban sustainable development.