Hello! I’m a final year PhD student at UC Berkeley, advised by Alexandre Bayen. Broadly speaking, my interests are in machine learning, optimization, and control, particularly problems concerning network dynamical systems, multi-agent learning systems, and transportation. My research goal is to advance computational methods to enable intelligent infrastructure.

Specifically, my research tackles the following areas:

  • Scalable deep reinforcement learning
  • Automatic discovery of policies for networked dynamical systems
  • Algorithms and inference for scalable mobility demand management

I recently interned at OpenAI, where I worked with Pieter Abbeel and Igor Mordatch, and Microsoft Research, where I worked with Eric Horvitz.

If you are interested in my work, please do get in touch.

Journal publications

[7] Automatic Discovery of Interpretable Policies for Regulating Mixed-Autonomy Traffic
Cathy Wu, et al.
Journal of Machine Learning Research (JMLR). In preparation.

[6] Clustering for set partitioning
Cathy Wu, Ece Kamar, Eric Horvitz
ACM Journal of Experimental Algorithmics (JEA). In preparation.

[5] Multi-lane Reduction: A Stochastic Single-lane Model for Lane Changing
Eugene Vinitsky, Cathy Wu, et al.
IEEE Transactions on Intelligent Vehicles (T-IV). In preparation.

[4] Flow: Architecture and Benchmarking for Reinforcement Learning in Traffic Control
Cathy Wu, Aboudy Kreidieh, Kanaad Parvate, Eugene Vinitsky, Alexandre Bayen
IEEE Transactions on Robotics (T-RO). In review, 2017. [arXiv][videos][github]

[3] Optimizing the diamond lane: A more tractable carpool problem and algorithms
Cathy Wu, K. Shankari, Ece Kamar, Randy Katz, David Culler, Christos Papadimitriou, Eric Horvitz, Alexandre Bayen
IEEE Transactions on Automation Science and Engineering (T-ASE). In review, 2017.

[2] Block simplex signal recovery: a method comparison and an application to routing
Cathy Wu, Alexei Pozdnoukhov, Alexandre Bayen
IEEE Transactions on Intelligent Transportation Systems (T-ITS). In review, 2017.

[1] Cellpath: fusion of cellular and traffic sensor data for route flow estimation via convex optimization
Cathy Wu, Jerome Thai, Steve Yadlowsky, Alexei Pozdnoukhov, Alexandre Bayen
Transportation Research: Part C, 2015. [journal] [pdf]


Conference publications

[10] Variance Reduction for Policy Gradient Using Action-Dependent Factorized Baselines
Cathy Wu, Aravind Rajeswaran, Yan Duan, Vikash Kumar, Alexandre M Bayen, Sham Kakade, Pieter Abbeel, Igor Mordatch
Contributed talk. Deep Reinforcement Learning Symposium (NIPS), 2017.
International Conference on Learning Representations (ICLR), 2018. In review. [Open Reviews]

[9] Stabilizing traffic with autonomous vehicles
Cathy Wu, Alexandre Bayen, Ankur Mehta
International Conference on Robotics and Automation (ICRA), 2018. In review.

[8] Emergent behaviors in mixed-autonomy traffic
Cathy Wu, Aboudy Kreidieh, Eugene Vinitsky, Alexandre Bayen
Conference on Robot Learning (CoRL), 2017.

[7] Framework for Control and Deep Reinforcement Learning in Traffic
Cathy Wu, Kanaad Parvate, Nishant Kheterpal, Leah Dickstein, Ankur Mehta, Eugene Vinitsky, Alexandre Bayen
IEEE Intelligent Transportation Systems Conference (ITSC), 2017.

[6] Multi-lane Reduction: A Stochastic Single-lane Model for Lane Changing
Cathy Wu, Eugene Vinitsky, Abdul Kreidieh, Alexandre Bayen
IEEE Intelligent Transportation Systems Conference (ITSC), 2017.

[5] Clustering for Set Partitioning with a Case Study in Ridesharing
Cathy Wu, Ece Kamar, Eric Horvitz
IEEE Intelligent Transportation Systems Conference (ITSC), 2016. Best paper award. [pdf]

[4] Optimizing the diamond lane: A more tractable carpool problem and algorithms
Cathy Wu, K. Shankari, Ece Kamar, Randy Katz, David Culler, Christos Papadimitriou, Eric Horvitz, Alexandre Bayen
IEEE Intelligent Transportation Systems Conference (ITSC), 2016. [pdf]

[3] Convex programming on the l1-ball and on the simplex via isotonic regression
Jerome Thai, Cathy Wu, Alexei Pozdnoukhov, Alexandre Bayen
Conference on Decision and Control (CDC), 2015. [pdf]

[2] Cellpath: fusion of cellular and traffic sensor data for route flow estimation via convex optimization
Cathy Wu, Jerome Thai, Steve Yadlowsky, Alexei Pozdnoukhov, Alexandre Bayen
International Symposium on Transportation and Traffic Theory (ISTTT), 2015. [proceedings] [pdf]

[1] Link Density Inference from Cellular Infrastructure
Steve Yadlowsky, Jerome Thai, Cathy Wu, Alexei Pozdnoukhov, Alexandre Bayen
Transportation Research Board (TRB) Annual Meeting and Transportation Research Record (TRR), 2015. [journal] [pdf]


General audience articles

[2] Traffic Jammin’: Making automated transportation a reality
Cathy Wu
Berkeley Science Review Magazine, 2016. [full article]

[1] Automating us: The entanglement of people and machines
Daniel Aranki*, Roel Dobbe*, Jaime F. Fisac*, and Cathy Wu*
Berkeley Science Review Magazine, 2015. [full article]


In the press

[3] ITS Announced Award Winners. Berkeley ITS, Apr 2017 [press release]

[2] Cathy Wu Selected as Rising Star. Berkeley ITS, Sept 2016 [press release]

[1] AT&T will improve your morning commute. AT&T press release, Sept 2015 [press release]


Selected talks

Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines
OpenAI, 2017.

Flow: Computational Framework for Deep RL and Traffic Microsimulation
SidewalkLabs, Alphabet, 2017.

Reinforcement Learning for Mixed-Autonomy Traffic
IEEE General Meeting, UC Berkeley, 2017. [slides]

Reinforcement Learning for Mixed-Autonomy Traffic
NSF Foundations Of Resilient CybEr-physical Systems (FORCES), Annual Meeting, UC Berkeley, 2017.

Mixed-Autonomy Traffic
IEEE Leaders Summit, 2017. [slides]

Towards Energy Minimization of Mixed-Autonomy Traffic via Control Theory and Reinforcement Learning
California Partners for Advanced Transportation Technology (PATH), UC Berkeley, 2016.

Cellpath: State Estimation of Traffic Networks via Convex Optimization
Distributed Robotics Lab, CSAIL, MIT, 2016.

Cellpath: State Estimation of Traffic Networks via Convex Optimization
Resilient Infrastructure Networks Lab, CEE, MIT, 2016.

Randomization for Ridesharing, Uber, 2015.

Cellpath: State Estimation of Static Traffic Networks via Convex Optimization
Women in Computer Science & Electrical Engineering (WISCE), Berkeley-Stanford Meetup, 2015. [slides]

Convex optimization for traffic assignment
Verizon, 2014.

Convex optimization for traffic assignment
AT&T, 2014.


*equal contribution