Back to researchers
John Schulman
Reinforcement learning, post-training
Key contributor to practical RL algorithms and RLHF-era post-training used in modern assistants.
Highlights
OpenAIRLHFRL
Focus: Reinforcement learning, post-training
Why it matters: Key contributor to practical RL algorithms and RLHF-era post-training used in modern assistants.
Research Areas
OpenAIRLHFRL