Group Expectation Policy Optimization for Heterogeneous Reinforcement Learning
Han Zhang, Ruibin Zheng, Zexuan Yi, Zhuo Zhang, Hanyang Peng, Hui Wang, Zike Yuan, Cai Ke, Shiwei Chen, Jiacheng Yang, Yangning Li, Xiang Li, Jiangyue Yan, Yaoqi Liu, Liwen Jing, Jiayin Qi, Ruifeng Xu, Binxing Fang, Yue Yu
Published: 2025/8/25
Abstract
As single-center computing approaches power constraints, decentralized training is becoming essential. Reinforcement Learning (RL) post-training enhances Large Language Models (LLMs) but faces challenges in heterogeneous distributed environments due to its tightly-coupled sampling-learning alternation. We propose HeteroRL, an asynchronous RL architecture that decouples rollout sampling from parameter learning, enabling robust deployment across geographically distributed nodes under network delays. We identify that latency-induced KL divergence causes importance sampling failure due to high variance. To address this, we propose Group Expectation Policy Optimization (GEPO), which reduces importance weight variance through a refined sampling mechanism. Theoretically, GEPO achieves exponential variance reduction. Experiments show it maintains superior stability over methods like GRPO, with less than 3% performance degradation under 1800-second delays, demonstrating strong potential for decentralized RL in heterogeneous networks.