Hybrid Group Relative Policy Optimization: A Multi-Sample Approach to Enhancing Policy Optimization

• URL: http://arxiv.org/abs/2502.01652v1
• Date: Thu, 30 Jan 2025 21:04:01 GMT
• Title: Hybrid Group Relative Policy Optimization: A Multi-Sample Approach to Enhancing Policy Optimization
• Abstract summary: Hybrid Group Relative Policy Optimization (Hybrid GRPO) is a reinforcement learning framework.<n>It incorporates empirical multi-sample action evaluation while preserving the stability of value function-based learning.<n>By integrating structured empirical sampling with reinforcement learning stability mechanisms, Hybrid GRPO has potential applications in autonomous robotics, financial modeling, and AI-driven control systems.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hybrid Group Relative Policy Optimization (Hybrid GRPO) is a reinforcement learning framework that extends Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) by incorporating empirical multi-sample action evaluation while preserving the stability of value function-based learning. Unlike DeepSeek GRPO, which eliminates the value function in favor of purely empirical reward estimation, Hybrid GRPO introduces a structured advantage computation method that balances empirical action sampling with bootstrapped value estimation. This approach enhances sample efficiency, improves learning stability, and mitigates variance amplification observed in purely empirical methods. A detailed mathematical comparison between PPO, DeepSeek GRPO, and Hybrid GRPO is presented, highlighting key differences in advantage estimation and policy updates. Experimental validation in a controlled reinforcement learning environment demonstrates that Hybrid GRPO achieves superior convergence speed, more stable policy updates, and improved sample efficiency compared to existing methods. Several extensions to Hybrid GRPO are explored, including entropy-regularized sampling, hierarchical multi-step sub-sampling, adaptive reward normalization, and value-based action selection. Beyond reinforcement learning in simulated environments, Hybrid GRPO provides a scalable framework for bridging the gap between large language models (LLMs) and real-world agent-based decision-making. By integrating structured empirical sampling with reinforcement learning stability mechanisms, Hybrid GRPO has potential applications in autonomous robotics, financial modeling, and AI-driven control systems. These findings suggest that Hybrid GRPO serves as a robust and adaptable reinforcement learning methodology, paving the way for further advancements in policy optimization.

Related papers

• AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO [78.36537400975298]
  Group Relative Policy Optimization (GRPO) has demonstrated remarkable success in aligning text-to-image (T2I) flow models with human preferences.<n>We have identified that the learning loop of current flow-based GRPO is fundamentally decoupled from the learner's current capability.<n>We propose Adaptive GRPO (AdaGRPO), a novel capability-aware RL algorithm tailored for flow models.
  arXiv  Detail & Related papers  (2026-06-05T02:07:08Z)
• M$^{2}$GRPO: Mamba-based Multi-Agent Group Relative Policy Optimization for Biomimetic Underwater Robots Pursuit [14.647568615794475]
  Mamba-based multi-agent group relative policy optimization (M$2$GRPO) is proposed.<n>It integrates a selective state-space Mamba policy with group-relative policy optimization under the centralized-training and decentralized-execution paradigm.<n>Overall, the proposed framework provides a practical and scalable solution for cooperative underwater pursuit with biomimetic robot systems.
  arXiv  Detail & Related papers  (2026-04-21T12:29:00Z)
• Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic [12.256817975993128]
  Relative policy optimization is a core methodological component of DeepSeekMath and DeepSeek-R1.<n>This paper provides a unified framework to understand GRPO through the lens of classical U-statistics.
  arXiv  Detail & Related papers  (2026-03-01T15:56:43Z)
• 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)
• GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization [133.27496265096445]
  We show how to apply Group Relative Policy Optimization under multi-reward setting without examining its suitability.<n>We then introduce Group reward-Decoupled Normalization Policy Optimization (GDPO), a new policy optimization method to resolve these issues.<n>GDPO consistently outperforms GRPO, demonstrating its effectiveness and generalizability for multi-reward reinforcement learning optimization.
  arXiv  Detail & Related papers  (2026-01-08T18:59:24Z)
• GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning [52.16150076582931]
  We propose Group Relative Policy Optimization for Representation Model (GRPO-RM)<n>Our method establishes a predefined output set to functionally replace token sequence sampling in large language models (LLMs)<n>A specialized reward function is designed to accommodate the properties of representation models.
  arXiv  Detail & Related papers  (2025-11-19T09:19:39Z)
• Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition [52.232968183793986]
  General Policy Composition (GPC) is a training-free method that enhances performance by combining the distributional scores of multiple pre-trained policies.<n>GPC consistently improves performance and adaptability across a diverse set of tasks.
  arXiv  Detail & Related papers  (2025-10-01T16:05:53Z)
• ACPO: Adaptive Curriculum Policy Optimization for Aligning Vision-Language Models in Complex Reasoning [17.928214942495412]
  ACPO employs a dynamic curriculum that orchestrates a principled transition from a stable, near on-policy exploration phase to an efficient, off-policy exploitation phase.<n>We conduct extensive experiments on a suite of challenging multimodal reasoning benchmarks, including MathVista, LogicVista, and MMMU-Pro.<n>Results demonstrate that ACPO consistently outperforms strong baselines such as DAPO and PAPO, achieving state-of-the-art performance, accelerated convergence, and superior training stability.
  arXiv  Detail & Related papers  (2025-10-01T09:11:27Z)
• Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces [57.466101098183884]
  Reinforcement learning (RL) struggles to scale to large, action spaces common in many real-world problems.<n>This paper introduces a novel framework for training discrete diffusion models as highly effective policies in complex settings.
  arXiv  Detail & Related papers  (2025-09-26T21:53:36Z)
• GRPOformer: Advancing Hyperparameter Optimization via Group Relative Policy Optimization [1.6759048077528458]
  We propose a novel framework that integrates reinforcement learning (RL) with Transformers.<n>In GRPOformer, Transformers are employed to generate new hyperparameter configurations from historical optimization trajectories.<n>We also introduce Policy Churn Regularization (PCR) to enhance the stability of GRPO training.
  arXiv  Detail & Related papers  (2025-09-21T14:54:51Z)
• 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)
• Geometric-Mean Policy Optimization [122.95205388291987]
  We propose a stabilized variant of Group Relative Policy Optimization ( GRPO)<n>Instead of optimizing the arithmetic mean, GMPO maximizes the geometric mean of token-level rewards.<n>Beyond improved stability, GMPO-7B outperforms GRPO by an average of 4.1% on multiple mathematical benchmarks and 1.4% on multimodal reasoning benchmark.
  arXiv  Detail & Related papers  (2025-07-28T09:54:05Z)
• Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training [19.783852824564736]
  We revisit Group Relative Policy Optimization (GRPO) in both on-policy and off-policy optimization regimes.<n>We show that both on-policy and off-policy GRPO objectives yield an improvement in the reward.<n>We then compare the empirical performance of reinforcement learning with verifiable rewards in post-training using both GRPO variants.
  arXiv  Detail & Related papers  (2025-05-28T11:42:33Z)
• Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach [2.8626097661711394]
  Reinforcement Learning from Human Feedback has achieved notable success in steering models, but is complex and can be unstable. Recent approaches such as Direct Preference Optimization (DPO) simplify preference-based fine-tuning but may introduce bias or trade-off certain objectives. We propose a Group Relative Policy Optimization framework with a multi-label reward regression model to achieve safe and aligned language generation.
  arXiv  Detail & Related papers  (2025-03-26T05:50:33Z)
• RL-finetuning LLMs from on- and off-policy data with a single algorithm [53.70731390624718]
  We introduce a novel reinforcement learning algorithm (AGRO) for fine-tuning large-language models. AGRO leverages the concept of generation consistency, which states that the optimal policy satisfies the notion of consistency across any possible generation of the model. We derive algorithms that find optimal solutions via the sample-based policy gradient and provide theoretical guarantees on their convergence.
  arXiv  Detail & Related papers  (2025-03-25T12:52:38Z)
• Evolutionary Policy Optimization [47.30139909878251]
  On-policy reinforcement learning (RL) algorithms are widely used for their strong performance and training stability, but they struggle to scale with larger batch sizes.<n>We propose Evolutionary Policy Optimization (EPO), a hybrid that combines the scalability and diversity of EAs with the performance and stability of policy gradients.
  arXiv  Detail & Related papers  (2025-03-24T18:08:54Z)
• Diffusion Policy Policy Optimization [37.04382170999901]
  Diffusion Policy Optimization, DPPO, is an algorithmic framework for fine-tuning diffusion-based policies.<n>DPO achieves the strongest overall performance and efficiency for fine-tuning in common benchmarks.<n>We show that DPPO takes advantage of unique synergies between RL fine-tuning and the diffusion parameterization.
  arXiv  Detail & Related papers  (2024-09-01T02:47:50Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• Gradient Based Hybridization of PSO [1.1059341532498634]
  Particle Swarm Optimization (PSO) has emerged as a powerful metaheuristic global optimization approach over the past three decades. PSO faces challenges, such as premature stagnation in single-objective scenarios and the need to strike a balance between exploration and exploitation. Hybridizing PSO by integrating its cooperative nature with established optimization techniques from diverse paradigms offers a promising solution.
  arXiv  Detail & Related papers  (2023-12-15T11:26:36Z)
• Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning [139.53668999720605]
  We present a multi-agent PPO algorithm in which the local policy of each agent is updated similarly to vanilla PPO. We prove that with standard regularity conditions on the Markov game and problem-dependent quantities, our algorithm converges to the globally optimal policy at a sublinear rate.
  arXiv  Detail & Related papers  (2023-05-08T16:20:03Z)
• Diverse Policy Optimization for Structured Action Space [59.361076277997704]
  We propose Diverse Policy Optimization (DPO) to model the policies in structured action space as the energy-based models (EBM) A novel and powerful generative model, GFlowNet, is introduced as the efficient, diverse EBM-based policy sampler. Experiments on ATSC and Battle benchmarks demonstrate that DPO can efficiently discover surprisingly diverse policies.
  arXiv  Detail & Related papers  (2023-02-23T10:48:09Z)
• Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble [43.95417785185457]
  It is challenging for reinforcement learning algorithms to succeed in real-world applications like financial trading and logistic system. We propose Ensemble Proximal Policy Optimization (EPPO), which learns ensemble policies in an end-to-end manner. EPPO achieves higher efficiency and is robust for real-world applications compared with vanilla policy optimization algorithms and other ensemble methods.
  arXiv  Detail & Related papers  (2022-05-19T02:25:32Z)
• Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling [68.69431580852535]
  We introduce a novel GP regression to incorporate the subgroup feedback. Our modified regression has provably lower variance -- and thus a more accurate posterior -- compared to previous approaches. We execute our algorithm on two disparate social problems.
  arXiv  Detail & Related papers  (2021-07-07T03:57:22Z)
• Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts [52.844741540236285]
  This paper investigates the model-based methods in multi-agent reinforcement learning (MARL) We propose a novel decentralized model-based MARL method, named Adaptive Opponent-wise Rollout Policy (AORPO)
  arXiv  Detail & Related papers  (2021-05-07T16:20:22Z)

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.