GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning

Understand

Reinforcement Learning (RL) can directly enhance the reasoning capabilities of large language models without extensive reliance on Supervised Fine-Tuning (SFT).

• In this work, we revisit the traditional Policy Gradient (PG) mechanism and propose a minimalist RL approach termed Group Policy Gradient (GPG).
• Unlike conventional methods, GPG directly optimize the original RL objective, thus obviating the need for surrogate loss functions.
• By eliminating the critic and reference models, avoiding KL divergence constraints, and addressing the advantage and gradient estimation bias, our approach significantly simplifies the training process compared to Group Relative Policy Optimization (GRPO).