Research
Completion-Aware Cross-Fidelity Offline-to-Online Reinforcement Learning for Multi-Line Bus Holding
arXiv:2609.39868v1 Announce Type: new Abstract: Exploratory reinforcement learning (RL) on an operating bus fleet is impractical,while policies trained only from historical data cannot acquire new exp
arXiv:2609.39868v1 Announce Type: new 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.
Related
- D^2Evo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning
- GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
- CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts
- On the Complexity of Offline Reinforcement Learning with Q^star-Approximation and Partial Coverage
Source: arXiv cs.AI | 2026-10-01