Sotabase

Career

· Machine Learning Consultant, Rebel Space Technologies2020–
· Research Assistant, UC Berkeley2016–
· PhD in Computer Science, University of California, Berkeley2016–
· Research Assistant, California Institute of Technology2015–2016
· B.S. in Computer Science, California Institute of Technology2012–2016
· Software Development Engineer Intern, Amazon
· Research Intern, Clarifai
· Research Intern, Google Brain
· Research Scientist, Google DeepMind
· Summer Undergraduate Research Fellow, NASA Jet Propulsion Lab
· Research Intern, Nervana Systems (Acquired by Intel)

Publications (21)

Entity Abstraction in Visual Model-Based Reinforcement Learning
Conference on Robot Learning · 2019
199
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
Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
International Conference on Machine Learning · 2018
153
cited
Small-scale proxies for large-scale Transformer training instabilities
International Conference on Learning Representations · 2023
142
cited
Evolving Reinforcement Learning Algorithms
International Conference on Learning Representations · 2021
76
cited
Guiding Policies with Language via Meta-Learning
International Conference on Learning Representations · 2018
67
cited
Improving Large Language Model Fine-tuning for Solving Math Problems
arXiv.org · 2023
66
cited
Ecological Reinforcement Learning
arXiv.org · 2020
24
cited
Information is Power: Intrinsic Control via Information Capture
Neural Information Processing Systems · 2021
10
cited
Differentiable Architecture Search for Reinforcement Learning
2021
5
cited
Multi-objective evolution for Generalizable Policy Gradient Algorithms
arXiv.org · 2022
5
cited
Intrinsic Control of Variational Beliefs in Dynamic Partially-Observed Visual Environments
2021
3
cited
A CCELERATING O NLINE R EINFORCEMENT L EARNING VIA M ODEL -B ASED M ETA -L EARNING
2021
1
cited
Building RL Algorithms that Generalize: From Latent Dynamics Models to Meta-Learning
2021
1
cited
Evolving Generalizable Actor-Critic Algorithms
2022
Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability
2022
Nervanasystems/Neon: New Data Loader (Aeon), Neural Machine Translation, Doc Updates And Bug Fixes
2016
Sotabase