Reinforcement learning for mode choice decisions (A07)

• Subject Area: Measurement Systems
• Term: since 2025
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 531327426

Project A7 seeks to explore the potential of Deep Reinforcement Learning (DRL) to develop models that handle dynamic mode choices, especially in scenarios with numerous and continuously changing alternatives. It also aims to investigate dynamic decision-making, where agents adapt as they move throughout the day, rather than planning all choices in advance. We will investigate how well a DRL agent can learn to make effective mode choice decisions compared to existing models, what initial strategies the agent develops in the MATSim environment, and how these strategies can be refined to produce more realistic decisions.

• DFG Programme: CRC/Transregios
• Subproject of: TRR 408: AgiMo: Data-driven agile planning for responsible mobility
• Applicant Institution: Technische Universität Dresden
• Project Head: Professor Dr. Ostap Okhrin