S
Sean Cole
2 things Sean uses or recommends, from 1 episode.
Sean's top picks
What Sean uses or recommends most, ranked by how often and how strongly. Paid ads are left out.
Uses and recommends it · 1 episode
"What we did initially was a closed loop PPO architecture. PPO is proximal policy optimization, an RL algorithm... this is primarily to keep feedback to the cells stable, and we found that the critic for PPO was particularly well aligned with how we wanted to do feedback."
All 2 of Sean's picks
- Proximal Policy Optimization (PPO) Uses and recommends it "What we did initially was a closed loop PPO architecture. PPO is proximal policy optimization, an RL algorithm... this is primarily to keep feedback to the cells stable, and we found that the critic for PPO was particularly well aligned with how we wanted to do feedback." Only Sean
- Cortical Labs Uses it "Some of you may have seen human brain cells playing Doom. So that's some of the work that I did in collaboration with Cortical Labs. So they kind of put brain cells on chips and I wrote the algorithms for it." Only Sean