Learning Heuristics for Transit Network Design and Improvement with Deep Reinforcement Learning

arXiv:2404.05894v1 Announce Type: new
Abstract: Transit agencies world-wide face tightening budgets. To maintain quality of service while cutting costs, efficient transit network design is essential. But planning a network of public transit routes is a challenging optimization problem. The most successful approaches to date use metaheuristic algorithms to search through the space of solutions by applying low-level heuristics that randomly alter routes in a network. The design of these low-level heuristics has a major impact on the quality of the …

abstract algorithms arxiv budgets costs cs.ai cs.lg cs.ne design face heuristics improvement network optimization planning public quality reinforcement reinforcement learning routes service transit type world