Geometric-Mean Policy Optimization

• URL: http://arxiv.org/abs/2507.20673v2
• Date: Fri, 26 Sep 2025 11:33:27 GMT
• Title: Geometric-Mean Policy Optimization
• Authors: Yuzhong Zhao, Yue Liu, Junpeng Liu, Jingye Chen, Xun Wu, Yaru Hao, Tengchao Lv, Shaohan Huang, Lei Cui, Qixiang Ye, Fang Wan, Furu Wei,
• Abstract summary: Group Relative Policy Optimization ( GRPO) has significantly enhanced the reasoning capability of large language models.<n> GRPO is observed to suffer from unstable policy updates when facing tokens with outlier importance-weighted rewards.<n>We propose Geometric-Mean Policy Optimization (GMPO) to improve the stability of GRPO through suppressing token reward outliers.
• Score: 117.05113769757172
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Group Relative Policy Optimization (GRPO) has significantly enhanced the reasoning capability of large language models by optimizing the arithmetic mean of token-level rewards. Unfortunately, GRPO is observed to suffer from unstable policy updates when facing tokens with outlier importance-weighted rewards, which manifest as extreme importance sampling ratios during training. In this study, we propose Geometric-Mean Policy Optimization (GMPO), with the aim to improve the stability of GRPO through suppressing token reward outliers. Instead of optimizing the arithmetic mean, GMPO maximizes the geometric mean of token-level rewards, which is inherently less sensitive to outliers and maintains a more stable range of importance sampling ratio. GMPO is plug-and-play-simply replacing GRPO's arithmetic mean with the geometric mean of token-level rewards, as the latter is inherently less sensitive to outliers. GMPO is theoretically plausible-analysis reveals that both GMPO and GRPO are weighted forms of the policy gradient while the former enjoys more stable weights, which consequently benefits policy optimization and performance. Experiments on multiple mathematical reasoning benchmarks show that GMPO-7B improves the average Pass@1 of GRPO by up to 4.1%, outperforming many state-of-the-art approaches. Code is available at https://github.com/callsys/GMPO.

Related papers

• Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization [60.87651283510059]
  Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs.<n>We propose Dynamic Pruning Policy Optimization (DPPO), a framework that enables dynamic pruning while preserving unbiased gradient estimation.<n>To mitigate the data sparsity induced by pruning, we introduce Dense Prompt Packing, a window-based greedy strategy.
  arXiv  Detail & Related papers  (2026-03-04T14:48:53Z)
• iGRPO: Self-Feedback-Driven LLM Reasoning [88.83313431248473]
  Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions.<n>We introduce Iterative Group Relative Policy Optimization (iGRPO), a two-stage extension of GRPO that adds dynamic self-conditioning through model-generated drafts.<n>Under matched rollout budgets, iGRPO consistently outperforms GRPO across base models.
  arXiv  Detail & Related papers  (2026-02-09T18:45:11Z)
• One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry [40.539393367855176]
  Group-based reinforcement learning has evolved from the arithmetic mean of GRPO to the geometric mean of GMPO.<n>We unify these approaches under Power-Mean Policy Optimization (PMPO), a generalized framework that parameterizes the aggregation geometry.<n>We show that adjusting p modulates the concentration of gradient updates, effectively reweighting tokens based on their advantage contribution.
  arXiv  Detail & Related papers  (2026-01-30T03:58:54Z)
• Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning [48.34492357368989]
  We propose a primal-dual framework that supports stable on-policy learning and enables principled off-policy data reuse.<n>$R2VPO$ achieves superior performance with average relative gains of up to 17% over strong clipping-based baselines.
  arXiv  Detail & Related papers  (2026-01-06T14:01:42Z)
• Anchoring Values in Temporal and Group Dimensions for Flow Matching Model Alignment [61.80228667422234]
  VGPO redefines value estimation across both temporal and group dimensions.<n>It transforms the sparse terminal reward into dense, process-aware value estimates.<n>It replaces standard group normalization with a novel process enhanced by absolute values to maintain a stable optimization signal.
  arXiv  Detail & Related papers  (2025-12-13T16:31:26Z)
• GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping [63.33669214116784]
  GRPO-Guard is a simple yet effective enhancement to existing GRPO frameworks.<n>It restores a balanced and step-consistent importance ratio, ensuring that PPO clipping properly constrains harmful updates.<n>It substantially mitigates implicit over-optimization without relying on heavy KL regularization.
  arXiv  Detail & Related papers  (2025-10-25T14:51:17Z)
• On the Theory and Practice of GRPO: A Trajectory-Corrected Approach with Fast Convergence [2.8165669455824696]
  Group Relative Policy Optimization is a critic-free reinforcement learning algorithm.<n>We show that GRPO update rule estimates the policy gradient at the old policy rather than the current one.<n>We propose a new algorithm: Trajectory level Importance Corrected GRPO.
  arXiv  Detail & Related papers  (2025-08-04T19:01:19Z)
• Mirror Descent Policy Optimisation for Robust Constrained Markov Decision Processes [8.735525389833013]
  This paper presents mirror descent policy optimisation for robust constrained Markov decision processes (RCMDPs)<n>We make use of policy gradient techniques to optimise both the policy (as a maximiser) and the transition kernel (as an adversarial minimiser) on the Lagrangian representing a constrained MDP.<n>Experiments confirm the benefits of mirror descent policy optimisation in constrained and unconstrained optimisation, and significant improvements are observed in robustness tests.
  arXiv  Detail & Related papers  (2025-06-29T09:55:52Z)
• BNPO: Beta Normalization Policy Optimization [9.60676665395923]
  We propose a novel policy optimization method that adaptively normalizes rewards using a Beta distribution with dynamically updated parameters.<n>We provide theoretical analysis demonstrating BNPO's variance-reducing properties and show that it generalizes both REINFORCE and GRPO under binary-valued reward settings.<n> Experimental results confirm that BNPO achieves state-of-the-art performance among policy optimization methods on reasoning tasks.
  arXiv  Detail & Related papers  (2025-06-03T13:28:57Z)
• Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning [11.708197376569016]
  Group Relative Policy Optimization ( GRPO) is proposed to compute the advantage for each output by subtracting the mean reward, as the baseline, for all outputs in the group.<n>It can lead to inaccurate advantage estimates in environments with highly noisy rewards, potentially introducing bias.<n>We propose a model, called Kalman Filter Enhanced Group Relative Policy Optimization (KRPO), by using lightweight Kalman filtering to dynamically estimate the latent reward mean and variance.
  arXiv  Detail & Related papers  (2025-05-12T13:09:49Z)
• The Role of Baselines in Policy Gradient Optimization [83.42050606055822]
  We show that the emphstate value baseline allows on-policy. emphnatural policy gradient (NPG) to converge to a globally optimal. policy at an $O (1/t) rate gradient. We find that the primary effect of the value baseline is to textbfreduce the aggressiveness of the updates rather than their variance.
  arXiv  Detail & Related papers  (2023-01-16T06:28:00Z)
• Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games [63.60117916422867]
  This paper focuses on the most basic setting of competitive multi-agent RL, namely two-player zero-sum Markov games. We propose a single-loop policy optimization method with symmetric updates from both agents, where the policy is updated via the entropy-regularized optimistic multiplicative weights update (OMWU) method. Our convergence results improve upon the best known complexities, and lead to a better understanding of policy optimization in competitive Markov games.
  arXiv  Detail & Related papers  (2022-10-03T16:05:43Z)
• You May Not Need Ratio Clipping in PPO [117.03368180633463]
  Proximal Policy Optimization (PPO) methods learn a policy by iteratively performing multiple mini-batch optimization epochs of a surrogate objective with one set of sampled data. Ratio clipping PPO is a popular variant that clips the probability ratios between the target policy and the policy used to collect samples. We show in this paper that such ratio clipping may not be a good option as it can fail to effectively bound the ratios. We show that ESPO can be easily scaled up to distributed training with many workers, delivering strong performance as well.
  arXiv  Detail & Related papers  (2022-01-31T20:26:56Z)
• Soft Actor-Critic with Cross-Entropy Policy Optimization [0.45687771576879593]
  We propose Soft Actor-Critic with Cross-Entropy Policy Optimization (SAC-CEPO) SAC-CEPO uses Cross-Entropy Method (CEM) to optimize the policy network of SAC. We show that SAC-CEPO achieves competitive performance against the original SAC.
  arXiv  Detail & Related papers  (2021-12-21T11:38:12Z)
• Understanding the Effect of Stochasticity in Policy Optimization [86.7574122154668]
  We show that the preferability of optimization methods depends critically on whether exact gradients are used. Second, to explain these findings we introduce the concept of committal rate for policy optimization. Third, we show that in the absence of external oracle information, there is an inherent trade-off between exploiting geometry to accelerate convergence versus achieving optimality almost surely.
  arXiv  Detail & Related papers  (2021-10-29T06:35:44Z)
• Risk-Sensitive Markov Decision Processes with Combined Metrics of Mean and Variance [3.062772835338966]
  This paper investigates the optimization problem of an infinite stage discrete time Markov decision process (MDP) with a long-run average metric. A performance difference formula is derived and it can quantify the difference of the mean-variance combined metrics of MDPs under any two different policies. A necessary condition of the optimal policy and the optimality of deterministic policies are derived.
  arXiv  Detail & Related papers  (2020-08-09T10:35:35Z)
• Provably Good Batch Reinforcement Learning Without Great Exploration [51.51462608429621]
  Batch reinforcement learning (RL) is important to apply RL algorithms to many high stakes tasks. Recent algorithms have shown promise but can still be overly optimistic in their expected outcomes. We show that a small modification to Bellman optimality and evaluation back-up to take a more conservative update can have much stronger guarantees.
  arXiv  Detail & Related papers  (2020-07-16T09:25:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.