Fair and Efficient Investment in Public Transportation

Designing a transit network requires many sequential route extension decisions, but their quality is often visible only after the full network is assembled. This delayed-feedback challenge lies at the heart of the Transit Route Network Design Problem (TRNDP), where route interactions can be deceptive: an extension that appears useful locally can create transfer bottlenecks, produce redundant overlap, or reduce overall throughput. To guide route construction under delayed simulator feedback, we introduce AlphaTransit, a search-based planning framework for cityscale bus network design. AlphaTransit couples Monte Carlo Tree Search (MCTS) with a neural policy-value network: the policy proposes route extensions, the value estimates downstream design quality, and search uses these predictions to refine each decision. This provides decision-time lookahead during route construction without running simulator rollouts inside the search tree. We evaluate AlphaTransit on a new Bloomington TRNDP benchmark with realistic road topology and censusderived demand, under mixed and full transit demand settings. In the Bloomington network, AlphaTransit attains the highest service rate in both demand settings, reaching 54.6% and 82.1%, respectively. Relative to reinforcement learning without search, these correspond to 9.9% and 11.4% service rate gains; relative to MCTS without learned guidance, they correspond to 2.5% and 11.2% gains. These results suggest that coupling learned guidance with MCTS is more effective than using either approach alone for transit network design. Our code and data are publicly available in https://github.com/poudel-bibek/AlphaTransit.

We introduce the \emph{Safe Bicycle Network with Bounded Detours} (\emph{SBNBD}) problem, motivated by upgrading rural road networks for bicycle traffic. Given an undirected graph with safe and unsafe edges, edge lengths, upgrade costs, terminal pairs, a budget, and a detour factor $α$, the task is to upgrade unsafe edges so that each terminal pair is connected by a safe path of length at most $α$ times its shortest-path distance in the original network. We study SBNBD from a parameterized perspective. We prove strong NP-hardness on restricted graph classes, including planar graphs of treewidth two, graphs with feedback vertex set number one, and graphs of maximum degree three, and complement these lower bounds with polynomial-time algorithms for trees and graphs of maximum degree two. We show fixed-parameter tractability for the number of unsafe edges and prove matching SETH-based lower bounds, a polynomial-kernel lower bound, and W-hardness for natural parameters. Our main structural result maps any instance to an equivalent instance with $O(\mathrm{fes}+p)$ vertices and edges, where $\mathrm{fes}$ is the feedback edge number and $p$ the number of terminal pairs; this yields fixed-parameter tractability for $\mathrm{fes}+p$. Finally, we evaluate ILP-based algorithms on OpenStreetMap road networks for small German municipalities and their surroundings. The instances have small treewidth upper bounds and moderate feedback edge structure. Preprocessing based on the $\mathrm{fes}+p$ reduction and tree-decomposition-based cut generation both improve exact solving, especially on harder instances. Experiments with different detour factors show that increasing $α$ can reduce the upgraded-edge length, revealing trade-offs between upgrade cost and allowed relative detours. Overall, structural graph parameters provide a useful algorithmic lens for safe bicycle-network design.

We tackle the Metro Network Expansion Problem (MNEP), a subset of the Transport Network Design Problem (TNDP), which focuses on expanding metro systems to satisfy travel demand. Traditional methods rely on exact and heuristic approaches that require expert-defined constraints to reduce the search space. Recently, deep reinforcement learning (Deep RL) has emerged due to its effectiveness in complex sequential decision-making processes-it remains, however, computationally expensive, environmentally costly, and requires additional engineering to interpret. We show that MNEP problems are small enough to not require Deep RL methods. Reformulating the MNEP as a Non-Markovian Rewards Decision Process (NMRDP), we use tabular RL to achieve similar performance with significantly fewer training episodes, additionally offering greater interpretability. Additionally, we incorporate social equity criteria into the reward functions, focusing on efficiency and fairness, highlighting the versatility of our method. Evaluated in real-world settings-Xi'an and Amsterdam-our method reduces total episodes by a factor of 18 and total carbon emissions by a factor of 12 on average, while remaining competitive with Deep RL. This approach offers a replicable, modular, interpretable, and resource-efficient solution with potential applications to other combinatorial optimization problems.