Sotabase

Career

· Research Intern, ByteDance2025–
· Resident, X, the moonshot factory2022–2022
· AI Resident, Google2019–2021
· Quantitative Research Intern, Options Market-Making, Citadel Securities2018–2018
· Computer Vision Prediction Intern, Zoox2018–2018
· Software Enginner Intern, Google2017–2017
· Year-Round Summer Data Science Intern, NASA Jet Propulsion Laboratory2016–2016
· Bachelor's Degree, Caltech2015–2019

Publications (26)

Rules of the Road: Predicting Driving Behavior With a Convolutional Model of Semantic Interactions
Computer Vision and Pattern Recognition · 2019
271
cited
When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?
arXiv.org · 2022
98
cited
Should I Run Offline Reinforcement Learning or Behavioral Cloning?
International Conference on Learning Representations · 2022
80
cited
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
International Conference on Machine Learning · 2023
66
cited
Latent Bandits Revisited
Neural Information Processing Systems · 2020
52
cited
Hierarchical Bayesian Bandits
International Conference on Artificial Intelligence and Statistics · 2021
44
cited
Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations
arXiv.org · 2023
34
cited
On the Sensitivity of Reward Inference to Misspecified Human Models
International Conference on Learning Representations · 2022
28
cited
Learning to Influence Human Behavior with Offline Reinforcement Learning
2023
25
cited
Latent Programmer: Discrete Latent Codes for Program Synthesis
International Conference on Machine Learning · 2020
24
cited
Confidence-Conditioned Value Functions for Offline Reinforcement Learning
International Conference on Learning Representations · 2022
21
cited
Deep Hierarchy in Bandits
International Conference on Machine Learning · 2022
21
cited
ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
International Conference on Learning Representations · 2023
20
cited
Non-Stationary Latent Bandits
arXiv.org · 2020
15
cited
Thompson Sampling with a Mixture Prior
International Conference on Artificial Intelligence and Statistics · 2021
14
cited
Multi-Task Off-Policy Learning from Bandit Feedback
International Conference on Machine Learning · 2022
11
cited
Compositional Generalization and Decomposition in Neural Program Synthesis
arXiv.org · 2022
8
cited
Non-Stationary Off-Policy Optimization
International Conference on Artificial Intelligence and Statistics · 2021
7
cited
Offline RL with Observation Histories: Analyzing and Improving Sample Complexity
arXiv.org · 2023
7
cited
Learning to Explore in POMDPs with Informational Rewards
International Conference on Machine Learning · 2024
2
cited
Sotabase
Joey Hong | Researcher Profile | Sotabase | Sotabase