Sotabase

Career

· Graduate Student, DataGood @ Berkeley2025–
· Ph.D. Candidate, University of California, Berkeley2016–2021
· Graduate Student Instructor, Stanford University2015–2016
· Bachelor of Science in Electrical Engineering and Computer Sciences, University of California, Berkeley2011–2015
· Amazon
· Researcher, Berkeley Artificial Intelligence Research Lab (BAIR)
· Research Intern, Google DeepMind
· Research Scientist, Google DeepMind
· Graduate Student Instructor, University of California, Berkeley
· Research Assistant, University of California, Berkeley
· Research Scientist, Waymo

Publications (30)

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
arXiv.org · 2020
2,396
cited
D4RL: Datasets for Deep Data-Driven Reinforcement Learning
arXiv.org · 2020
1,639
cited
Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction
Neural Information Processing Systems · 2019
1,199
cited
When to Trust Your Model: Model-Based Policy Optimization
Neural Information Processing Systems · 2019
1,109
cited
Learning Robust Rewards with Adversarial Inverse Reinforcement Learning
International Conference on Learning Representations · 2017
819
cited
Learning Robust Rewards with Adverserial Inverse Reinforcement Learning
International Conference on Learning Representations · 2018
238
cited
Learning to Reach Goals via Iterated Supervised Learning
International Conference on Learning Representations · 2019
208
cited
One-shot learning of manipulation skills with online dynamics adaptation and neural network priors
IEEE/RJS International Conference on Intelligent RObots and Systems · 2015
167
cited
Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research
Neural Information Processing Systems · 2023
162
cited
EX2: Exploration with Exemplar Models for Deep Reinforcement Learning
Neural Information Processing Systems · 2017
160
cited
Diagnosing Bottlenecks in Deep Q-learning Algorithms
International Conference on Machine Learning · 2019
149
cited
Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios
IEEE/RJS International Conference on Intelligent RObots and Systems · 2022
144
cited
From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
International Conference on Learning Representations · 2019
137
cited
Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition
Neural Information Processing Systems · 2018
130
cited
Benchmarks for Deep Off-Policy Evaluation
International Conference on Learning Representations · 2021
110
cited
Generalizing Skills with Semi-Supervised Reinforcement Learning
International Conference on Learning Representations · 2016
70
cited
Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving
IEEE/RJS International Conference on Intelligent RObots and Systems · 2022
69
cited
Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation
International Conference on Learning Representations · 2021
58
cited
CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning
North American Chapter of the Association for Computational Linguistics · 2022
51
cited
Learning To Reach Goals Without Reinforcement Learning
arXiv.org · 2019
37
cited
Sotabase
Justin Fu | Researcher Profile | Sotabase | Sotabase