← Back

PPO

technique Endorsed by 1 creator

Proximal Policy Optimization, a reinforcement learning algorithm

Endorsed by

Greg Brockman

Topics

ai reinforcement learning algorithm

Used by

These creators have mentioned using this product

Greg Brockman uses
"The algorithm we use called PPO, you plan over every single time step. There's no hierarchy."
OpenAI Co-Founder on the AI Race, the Sam Altman Firing, and What Comes Next · ▶ 9:00 · Apr 2026