Sotabase

Career

· Cofounder and Chief Scientist, Thinking Machines2025–
· Research Scientist, Anthropic2024–
· Co-founder and Lead of Reinforcement Learning Team, OpenAI2015–

Publications (186)

GPT-4 Technical Report
2023
21,596
cited
Trust Region Policy Optimization
International Conference on Machine Learning · 2015
7,583
cited
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
Neural Information Processing Systems · 2016
4,432
cited
High-Dimensional Continuous Control Using Generalized Advantage Estimation
International Conference on Learning Representations · 2015
4,104
cited
GPT-4o System Card
arXiv.org · 2024
2,980
cited
Concrete Problems in AI Safety
arXiv.org · 2016
2,821
cited
On First-Order Meta-Learning Algorithms
arXiv.org · 2018
2,476
cited
Let's Verify Step by Step
International Conference on Learning Representations · 2023
2,424
cited
Theano: A Python framework for fast computation of mathematical expressions
arXiv.org · 2016
2,366
cited
Benchmarking Deep Reinforcement Learning for Continuous Control
International Conference on Machine Learning · 2016
1,779
cited
Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
Robotics: Science and Systems · 2017
1,276
cited
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
arXiv.org · 2016
1,109
cited
Motion planning with sequential convex optimization and convex collision checking
Int. J. Robotics Res. · 2014
911
cited
#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
Neural Information Processing Systems · 2016
828
cited
VIME: Variational Information Maximizing Exploration
Neural Information Processing Systems · 2016
814
cited
Transparent Water-in-Oil Dispersions: the Oleopathic Hydro-Micelle
Nature · 1943
779
cited
Variational Lossy Autoencoder
International Conference on Learning Representations · 2016
695
cited
Mechanism of Formation and Structure of Micro Emulsions by Electron Microscopy
1959
601
cited
Finding Locally Optimal, Collision-Free Trajectories with Sequential Convex Optimization
Robotics: Science and Systems · 2013
531
cited
Gradient Estimation Using Stochastic Computation Graphs
Neural Information Processing Systems · 2015
403
cited
Sotabase
John Schulman | Researcher Profile | Sotabase | Sotabase