Cathy Wu
An associate professor at MIT whose research uses reinforcement learning and multi-agent systems to optimize complex social systems such as urban transportation. Her work spans the Department of Civil and Environmental Engineering and the Institute for Data, Systems, and Society, and she promotes the development of open-source traffic simulation platforms.
Timeline (last 90 days)
MIT associate professor Cathy Wu's research direction is using reinforcement learning to provide computational tools for socially complex systems such as transportation, and her work spans the Department of Civil and Environmental Engineering and the Institute for Data, Systems, and Society.
Cathy Wu's team's reinforcement learning method does not require perfect a priori modeling of the transportation system, but instead gradually approaches better solutions through trial and error and reward signals.
Cathy Wu's research emphasizes system-level resilience, focusing on how the entire transportation network redistributes traffic and maintains service levels when nodes fail.
Cathy Wu has helped advance traffic simulation platforms that let researchers test RL strategies in virtual cities, lowering the barrier from algorithm to deployment.
The open-source tools advanced by Cathy Wu's team emphasize calibration with real data, making the simulation environment as close as possible to the traffic distribution and travel behavior of real road networks.
Cathy Wu's research emphasizes collaboration with policymakers and urban planners, embedding computational tools into real decision-making processes rather than replacing human judgment with algorithms.
Cathy Wu's methodology can be transferred to energy scheduling, supply chains, public health, and other domains equally full of uncertainty and multi-agent games.
All Facts (7)
MIT associate professor Cathy Wu's research direction is using reinforcement learning to provide computational tools for socially complex systems such as transportation, and her work spans the Department of Civil and Environmental Engineering and the Institute for Data, Systems, and Society.
50%UnverifiedCathy Wu's team's reinforcement learning method does not require perfect a priori modeling of the transportation system, but instead gradually approaches better solutions through trial and error and reward signals.
50%UnverifiedCathy Wu's research emphasizes system-level resilience, focusing on how the entire transportation network redistributes traffic and maintains service levels when nodes fail.
50%UnverifiedCathy Wu has helped advance traffic simulation platforms that let researchers test RL strategies in virtual cities, lowering the barrier from algorithm to deployment.
50%UnverifiedThe open-source tools advanced by Cathy Wu's team emphasize calibration with real data, making the simulation environment as close as possible to the traffic distribution and travel behavior of real road networks.
50%UnverifiedCathy Wu's research emphasizes collaboration with policymakers and urban planners, embedding computational tools into real decision-making processes rather than replacing human judgment with algorithms.
50%UnverifiedCathy Wu's methodology can be transferred to energy scheduling, supply chains, public health, and other domains equally full of uncertainty and multi-agent games.
50%