Scaling Laws for Collapse in Asynchronous GRPO

arXiv:2607.01083 · cs.LG, cs.AI · Submitted 2026-07-01 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-07-01

Updated: 2026-09-27

Terminology

• GRPO — 46× in this paper · explained in 6 episodes
• Cosine Similarity — 7× in this paper · explained in 3 episodes
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Scaling Laws — 6× in this paper · explained in 4 episodes
• Actor — 5× in this paper · explained in 3 episodes
• Distribution Shift — 5× in this paper · explained in 5 episodes
• Decoupling — 4× in this paper · explained in 2 episodes
• Regularization — 4× in this paper · explained in 3 episodes
• Fine-Tuning — 3× in this paper · explained in 5 episodes
• KL Regularization — 3× in this paper · explained in 2 episodes
• Group Relative Policy Optimization — 2× in this paper
• Trace — 2× in this paper · explained in 2 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• In International Conference on Machine Learning — 1× in this paper
• International Conference on Learning Representations — 1× in this paper
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Proximal Policy Optimization — 1× in this paper
• Proximal Policy Optimization (PPO) — 1× in this paper · explained in 4 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Training Compute-Optimal Large Language Models
• Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform
• Scaling Laws for Neural Language Models
• A Survey of Reinforcement Learning from Human Feedback
• An Empirical Model of Large-Batch Training
• Massively Parallel Methods for Deep Reinforcement Learning
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks