Sotabase

Career

· Research Scientist, Google Research2019–
· Research Scientist, Google DeepMind2017–2019
· Research Scientist, Osaro, Inc2016–2017
· Ph.D. in Computational and Mathematical Engineering, Stanford University2011–2017
· MSE in Aerospace Engineering, Purdue University2009–2011
· B.Eng. in Mechanical Engineering, University of Hong Kong2005–2009
· Google DeepMind

Publications (90)

Gemma 3 Technical Report
arXiv.org · 2025
882
cited
A Lyapunov-based Approach to Safe Reinforcement Learning
Neural Information Processing Systems · 2018
590
cited
Risk-Constrained Reinforcement Learning with Percentile Risk Criteria
Journal of machine learning research · 2015
588
cited
Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach
Neural Information Processing Systems · 2015
365
cited
DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections
Neural Information Processing Systems · 2019
357
cited
Lyapunov-based Safe Policy Optimization for Continuous Control
arXiv.org · 2019
282
cited
More Robust Doubly Robust Off-policy Evaluation
International Conference on Machine Learning · 2018
280
cited
AlgaeDICE: Policy Gradient from Arbitrary Experience
arXiv.org · 2019
258
cited
Algorithms for CVaR Optimization in MDPs
Neural Information Processing Systems · 2014
220
cited
Safe Policy Improvement by Minimizing Robust Baseline Regret
Neural Information Processing Systems · 2016
140
cited
Policy Gradient for Coherent Risk Measures
Neural Information Processing Systems · 2015
131
cited
CoinDICE: Off-Policy Confidence Interval Estimation
Neural Information Processing Systems · 2020
89
cited
Sequential Decision Making With Coherent Risk
IEEE Transactions on Automatic Control · 2017
72
cited
A Framework for Time-Consistent, Risk-Sensitive Model Predictive Control: Theory and Algorithms
IEEE Transactions on Automatic Control · 2019
70
cited
Online Modified Greedy algorithm for storage control under uncertainty
IEEE Power & Energy Society General Meeting · 2014
63
cited
Efficient Risk-Averse Reinforcement Learning
Neural Information Processing Systems · 2022
54
cited
Latent Bandits Revisited
Neural Information Processing Systems · 2020
52
cited
Path Consistency Learning in Tsallis Entropy Regularized MDPs
International Conference on Machine Learning · 2018
49
cited
CAQL: Continuous Action Q-Learning
International Conference on Learning Representations · 2019
48
cited
Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models
International Conference on Learning Representations · 2024
48
cited
Sotabase
Yinlam Chow | Researcher Profile | Sotabase | Sotabase