← Back
technique
Proximal Policy Optimization (PPO)
1 creator use or recommend it
▲ 1 active in the last 90 days
1 use
Last discussed Oct 2, 2026
A reinforcement learning algorithm that uses clipped policy updates and an actor-critic setup.
Recently discussed in
What If We Stopped Using GPUs? | YC Paper Club
Sean Cole · Oct 2, 2026
What creators say
SC
Sean Cole
uses
Used for: Training the encoder/decoder and modulating feedback to neuron cultures playing Doom
Praised: The critic is well aligned with stable feedback to the cells and enables surp...
vs: Used an entropy penalty instead of the usual entropy bonus
"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 w..."
More from Sean Cole →Keep exploring
Topics
About this data
- ✓44,000+ mentions extracted from real podcast transcripts
- ✓Every quote links to the source episode
- ✓Sponsored mentions are always labeled
- ✓Critical takes are shown, never filtered out
Get an email when a new creator recommends it