Estimating Link Flows in Road Networks with Synthetic Trajectory Data Generation: Reinforcement Learning-based Approaches

no code implementations • 26 Jun 2022 • Miner Zhong, Jiwon Kim, Zuduo Zheng

To ensure the generated population vehicle trajectories are consistent with the observed traffic volume and trajectory data, two methods based on Inverse Reinforcement Learning and Constrained Reinforcement Learning are proposed.

Decision Making reinforcement-learning +1