Score: 0

GPG: Generalized Policy Gradient Theorem for Transformer-based Policies

Published: December 11, 2025 | arXiv ID: 2512.10365v1

By: Hangyu Mao, Guangting Dong, Zhicheng Dou

Potential Business Impact:

Teaches AI to learn better and faster.

Business Areas:
Power Grid Energy

We present the Generalized Policy Gradient (GPG) Theorem, specifically designed for Transformer-based policies. Notably, we demonstrate that both standard Policy Gradient Theorem and GRPO emerge as special cases within our GPG framework. Furthermore, we explore its practical applications in training Large Language Models (LLMs), offering new insights into efficient policy optimization.

Country of Origin
🇨🇳 China

Page Count
14 pages

Category
Computer Science:
Machine Learning (CS)