← Back
technique
GRPO
Last discussed Aug 12, 2026
Group Relative Policy Optimization - a reinforcement learning algorithm used in training language models.
Recently discussed in
Chelsea Finn: This is the State of the Art in Robotics
Chelsea Finn · Aug 12, 2026
State of AI in 2026: LLMs, Coding, Scaling Laws, China, Agents, GPUs, AGI | Lex Fridman Podcast #490
Nathan Lambert · Jan 31, 2026
What creators say
CF
Chelsea Finn
mentioned
vs: Contrasted with Physical Intelligence's more sample-efficient RL approach for...
"In language models, we have algorithms like PPO and GRPO and these have scaled to large language models and have enabled really complex reasoning."
More from Chelsea Finn →
NL
Nathan Lambert
mentioned
"If we look at the GRPO equation, this one is famous for this because essentially the reward given to the agent is based on how good a given action—an action is a completion—is relative to the other answers to that same problem."
More from Nathan Lambert →Keep exploring
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