LGCLOct 27, 2025

Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts

arXiv:2510.23027v11 citationsh-index: 41
Originality Incremental advance
AI Analysis

This addresses a specific problem for researchers and practitioners working with large-scale MoE models, offering an incremental improvement in RL training stability.

The paper tackles the instability in reinforcement learning (RL) training for Mixture-of-Experts (MoE) architectures by proposing a router-aware approach to optimize importance sampling weights, resulting in improved convergence stability and final performance of MoE models.

Recent advances in reinforcement learning (RL) have substantially improved the training of large-scale language models, leading to significant gains in generation quality and reasoning ability. However, most existing research focuses on dense models, while RL training for Mixture-of-Experts (MoE) architectures remains underexplored. To address the instability commonly observed in MoE training, we propose a novel router-aware approach to optimize importance sampling (IS) weights in off-policy RL. Specifically, we design a rescaling strategy guided by router logits, which effectively reduces gradient variance and mitigates training divergence. Experimental results demonstrate that our method significantly improves both the convergence stability and the final performance of MoE models, highlighting the potential of RL algorithmic innovations tailored to MoE architectures and providing a promising direction for efficient training of large-scale expert models.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes