Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients

arXiv:2601.23135 · cs.LG · Submitted 2026-01-30 · Read on arXiv

cs.LG

Submitted: 2026-01-30

Updated: 2026-10-01

Terminology

• GRPO — 4× in this paper · explained in 6 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes

Sources

• Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs
• Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes
• MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
• GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
• Training Verifiers to Solve Math Word Problems
• Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
• Handbook of Convergence Theorems for (Stochastic) Gradient Methods
• Constrained Group Relative Policy Optimization
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Measuring Mathematical Problem Solving With the MATH Dataset
• Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
• Reinforcement Learning from Human Feedback
• Tulu 3: Pushing Frontiers in Open Language Model Post-Training
• The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
• ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
• Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits
• CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
• Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
• Understanding R1-Zero-Like Training: A Critical Perspective

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks