Sotabase

Career

· Senior Staff Research Scientist, Google DeepMind2023–
· PhD in Machine Learning, University of Cambridge2014–
· Intern, Google Brain
· Research Scientist, Google Research, Brain Team
· Visiting Associate Professor, University of Tokyo
· B.ASc. in Engineering Science, University of Toronto

Publications (71)

Large Language Models are Zero-Shot Reasoners
Neural Information Processing Systems · 2022
6,286
cited
Categorical Reparameterization with Gumbel-Softmax
International Conference on Learning Representations · 2016
5,977
cited
Scaling Instruction-Finetuned Language Models
Journal of machine learning research · 2022
3,860
cited
Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates
IEEE International Conference on Robotics and Automation · 2016
1,555
cited
Continuous Deep Q-Learning with Model-based Acceleration
International Conference on Machine Learning · 2016
1,056
cited
A Minimalist Approach to Offline Reinforcement Learning
Neural Information Processing Systems · 2021
1,019
cited
Data-Efficient Hierarchical Reinforcement Learning
Neural Information Processing Systems · 2018
927
cited
Towards Deep Neural Network Architectures Robust to Adversarial Examples
International Conference on Learning Representations · 2014
883
cited
Large Language Models Can Self-Improve
Conference on Empirical Methods in Natural Language Processing · 2022
775
cited
Dynamics-Aware Unsupervised Discovery of Skills
International Conference on Learning Representations · 2019
460
cited
Aligning Text-to-Image Models using Human Feedback
arXiv.org · 2023
400
cited
Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
arXiv.org · 2019
376
cited
Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
International Conference on Learning Representations · 2016
357
cited
A Divergence Minimization Perspective on Imitation Learning Methods
Conference on Robot Learning · 2019
276
cited
Temporal Difference Models: Model-Free Deep RL for Model-Based Control
International Conference on Learning Representations · 2018
255
cited
Categorical Reparametrization with Gumble-Softmax
International Conference on Learning Representations · 2017
246
cited
Language as an Abstraction for Hierarchical Deep Reinforcement Learning
Neural Information Processing Systems · 2019
240
cited
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning
International Conference on Learning Representations · 2018
225
cited
Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control
International Conference on Machine Learning · 2016
204
cited
Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning
Neural Information Processing Systems · 2017
172
cited
Sotabase
Shixiang(Shane) Gu | Researcher Profile | Sotabase | Sotabase