Jesse Zhang

Jesse Zhang

CS PhD Candidate

University of Southern California

Biography

Hi! I am a first-year PhD candidate at USC, working with Professor Joseph Lim on tackling problems in deep reinforcement learning. I completed my undergrad at UC Berkeley, where I worked with Professors Sergey Levine and Dinesh Jayaraman.

Interests

  • Deep RL
  • Offline Reinforcement Learning
  • Online Adaptation

Education

  • CS PhD Candidate, 2020 - ?

    USC

  • BA in Computer Science, 2016 - 2020

    UC Berkeley

Recent Publications

Quickly discover relevant content by filtering publications.

Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings

Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, …
Jesse Zhang, Brian Cheung, Chelsea Finn, Sergey Levine, Dinesh Jayaraman
PDF Code Project Poster Slides Video
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings

MobilityNet: Towards A Public Dataset For Multi-Modal Mobility Research

Influencing transportation demand can significantly reduce CO2 emissions. Individual user mobility models are key to influencing demand …
Kalyanaraman Shankari, Jonathan Fuerst, Mauricio Fadel Argerich, Eleftherios Avramidis, Jesse Zhang
PDF Code Project Poster Slides Video
MobilityNet: Towards A Public Dataset For Multi-Modal Mobility Research

TripAware: Emotional and Informational Approaches to Encourage Sustainable Transportation via Mobile Applications

To combat climate change, we need to change user transportation behavior to be less carbon intensive. Prior work on motivating this …
Jesse Zhang, John Sullivan, Vasudev Venkatesh PB, Kyle Tse, Andy Yan, John Leyden, Kalyanaraman Shankari, Randy H Katz
PDF Project
TripAware: Emotional and Informational Approaches to Encourage Sustainable Transportation via Mobile Applications

Unsupervised Projection Networks for Generative Adversarial Networks

We propose the use of unsupervised learning to train projection networks that project onto the latent space of an already trained …
Daiyaan Arfeen, Jesse Zhang
PDF
Unsupervised Projection Networks for Generative Adversarial Networks

Replab: A reproducible low-cost arm benchmark platform for robotic learning

Standardized evaluation measures have aided in the progress of machine learning approaches in disciplines such as computer vision and …
Brian Yang, Jesse Zhang, Vitchyr Pong, Sergey Levine, Dinesh Jayaraman
PDF Code Dataset Project
Replab: A reproducible low-cost arm benchmark platform for robotic learning