00

Group Relative Policy Optimization

Technique ☆ WATCH ⎘ SHARE

First seen 9/3/2026

Last seen 9/3/2026

Evidence 6 chunks

01

NEIGHBORHOOD

4 nodes · 4 edges

graph · Group Relative Policy Optimization · depth=1

02

RELATIONSHIPS

3 connections

GRPO with State Mutation ← extends 100% 2e evidence

GRPO-SMu modifies and improves upon conventional GRPO by diversifying input states.

reinforcement learning for language models implements → 100% 2e evidence

GRPO is a specific RL technique applied to language model training.

DeepSeekMath: pushing the limits of mathematical reasoning in open language models ← introduces 100% 1e evidence

The DeepSeekMath paper originally proposed the GRPO technique.