Cathy Wu grew up in a Taiwanese immigrant family where her father's long commute sparked an early interest in transportation. Playing games like SimCity during her childhood and attending a lecture on autonomous vehicles at MIT led her to pursue AI for traffic systems. Wu is now an associate professor in MIT's Department of Civil and Environmental Engineering and the Institute for Data, Systems, and Society, focusing on machine learning and reinforcement learning (RL) to make transportation more reliable and efficient.\ \ Designing transportation networks traditionally requires evaluating hundreds or thousands of variants, a task beyond current evidence‑driven tools. Wu argues that RL can automatically explore this massive design space, freeing researchers from manual analysis. During her PhD at UC Berkeley she applied RL to assess the impact of autonomous vehicles on various traffic networks, a study that attracted wide attention.\ \ Subsequent attempts to extend RL to other traffic problems failed, highlighting RL's sensitivity to problem specifics. In 2023 her team introduced a contextual RL approach: first identify the small subset (≈10%) of problems where RL trains well, then train models on this subset. The resulting models generalize to a broader set of related problems, cutting the number of required training runs from about 100 to roughly 3 and boosting training efficiency by up to 30×.\ \ Building on this, they tackled an eco‑driving optimization problem—intelligently controlling vehicle speeds to reduce stop‑and‑go behavior. The RL‑derived policy can cut vehicle emissions by 11%–22%, providing concrete evidence that data‑driven policies can substantially improve system efficiency. This work demonstrates RL’s practical relevance for transportation policy.\ \ Wu describes her research style as "use‑inspired basic research," developing algorithms that solve hard optimization problems in transportation, logistics, supply chains, and resource allocation while generating fundamental knowledge applicable elsewhere. She advises students to be patient, start small, stay curious, and ask many questions. Her contributions have earned a 2023 NSF CAREER award and the 2025 Ole Madsen Mentoring Award.\ \ Review