2 papers
cs.LG2026
GRPO Training Dynamics for Small Language Models
Rajat Ghosh, Vaishnavi Bhargava, Henry Wong +2
Group Relative Policy Optimization (GRPO) has emerged as a memory-efficient reinforcement fine-tuning (RFT) technique for reasoning-intensive tasks. How- ever, GRPO training dynami…
cs.LG2026
Predictable GRPO: A Closed-Form Model of Training Dynamics
Rajat Ghosh, Datta Nimmaturi, Aryan Singhal +4
We develop a first-principles reduced-order model of these dynamics. Under a single mean-field assumption that summarizes the policy by its expected reward, we reduce the GRPO upda…