Completion-Aware Cross-Fidelity Offline-to-Online Reinforcement Learning for Multi-Line Bus Holding

Abstract:Exploratory reinforcement learning (RL) on an operating bus fleet is impractical,while policies trained only from historical data cannot acquire new experience. Hybrid Offline-and-Online (H2O) RL combines fixed target replay with simulator interaction, but the inexpensive online simulator can differ from the target in transition and event-duration dynamics. We study this cross-fidelity problem for multi-line bus holding and address a failure mode in which lower generalized passenger time coexists with incomplete passenger journeys.

Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

arXiv:2609.39868 [cs.AI]

(or arXiv:2609.39868v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2609.39868 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.