Justin Fu
Research scientist at Waymo Research and lead developer of the open-source Waymax driving simulator
Justin Fu is a machine learning researcher at Waymo Research. Fu's CV describes the role of lead developer for Waymax, an open-source, hardware-accelerated simulator for planning and behavior research in autonomous driving, and Fu is one of four equal-contribution first authors of the Waymax paper. Before Waymo, Fu completed a PhD at UC Berkeley advised by Sergey Levine, with research on reinforcement learning including the D4RL benchmark.1235
Career
Fu completed a PhD in electrical engineering and computer sciences at UC Berkeley from 2016 to 2021, advised by Sergey Levine. During the PhD, Fu was a student researcher at Google and a research intern at DeepMind, working on inverse reinforcement learning.12
Fu joined Waymo as a research scientist in August 2021. Fu's CV lists work on reinforcement-learning fine-tuning of driving foundation models and on combining such models with search and optimization for reliability.2
Research
Fu's research covers reinforcement learning, natural language processing and robotics. Fu was first author of D4RL (2020), datasets for deep data-driven reinforcement learning, and co-organized the NeurIPS 2021 Workshop on Offline Reinforcement Learning.125
At Waymo, Fu was lead developer of Waymax, released in 2023 as an open-source simulator for planning and behavior problems in autonomous driving. The Waymax paper lists Cole Gulino, Fu, Wenjie Luo and George Tucker as equal-contribution first authors.234
Work
WaymaxOpen-source code
Lead developer of Waymax and an equal-contribution first author of its 2023 paper, which presents an accelerated, data-driven simulator for large-scale autonomous driving research.234
D4RL (external site: arxiv.org)Open data
First author of D4RL (2020), a set of datasets and benchmarks for offline, data-driven reinforcement learning.5
Career timeline
Aug 2016
Began a PhD in electrical engineering and computer sciences at UC Berkeley, advised by Sergey Levine.2
Jun 2018
Began work as a student researcher and research intern at Google.2
Sep 2019
Started a research internship at DeepMind on multi-agent inverse reinforcement learning.2
Apr 2020
Posted D4RL, datasets for deep data-driven reinforcement learning, as first author.5
Aug 2021
Joined Waymo as a research scientist.2
Oct 2023
Posted the Waymax simulator paper as an equal-contribution first author.32
Other documented roles
Roles the sources document but that are not confirmed as current.
Related people
More sourced profiles at the same organization, in the same field, or from the same school.
- Dmitri DolgovAlso at Waymo
- Bob McGrewRobotics
- Adam GleaveAlso at DeepMind
- Satish JeyachandranAlso at Waymo
- Chelsea FinnAlso at Google
- Alex SmolaAlso at Google Research
- Tekedra MawakanaAlso at Waymo
- Deepak PathakAlso from UC Berkeley
- Alexei A. EfrosAlso from UC Berkeley
- Abhimanyu DasAlso at Google
- Gavriel StateRobotics
- Ali GhodsiAlso from UC Berkeley
Is this you?
Profiles cover public professional work only, and every line cites a source. If something is out of date, missing or wrong, send a correction with a link to an official page and we will update it. Suggest a correction
Add this badge to your website or GitHub profile README. It links back to this page. It is not an endorsement or a rating.
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/people/justin-fu/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/people/justin-fu/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/profile.svg" alt="Justin Fu — Profile on USASI" height="20"></a>
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.