AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models

• URL: http://arxiv.org/abs/2602.06825v1
• Date: Fri, 06 Feb 2026 16:09:50 GMT
• Title: AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models
• Authors: Yuming Li, Qingyu Li, Chengyu Bai, Xiangyang Luo, Zeyue Xue, Wenyu Qin, Meng Wang, Yikai Wang, Shanghang Zhang,
• Abstract summary: Reinforcement learning from human feedback shows promise for aligning diffusion and flow models.<n>Policy optimization methods such as GRPO suffer from inefficient and static sampling strategies.<n>We propose Adaptive Entropy-Guided Policy Optimization (AEGPO), a novel dual-signal, dual-level adaptive optimization strategy.
• Score: 54.56296715999545
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning from human feedback (RLHF) shows promise for aligning diffusion and flow models, yet policy optimization methods such as GRPO suffer from inefficient and static sampling strategies. These methods treat all prompts and denoising steps uniformly, ignoring substantial variations in sample learning value as well as the dynamic nature of critical exploration moments. To address this issue, we conduct a detailed analysis of the internal attention dynamics during GRPO training and uncover a key insight: attention entropy can serve as a powerful dual-signal proxy. First, across different samples, the relative change in attention entropy (ΔEntropy), which reflects the divergence between the current policy and the base policy, acts as a robust indicator of sample learning value. Second, during the denoising process, the peaks of absolute attention entropy (Entropy(t)), which quantify attention dispersion, effectively identify critical timesteps where high-value exploration occurs. Building on this observation, we propose Adaptive Entropy-Guided Policy Optimization (AEGPO), a novel dual-signal, dual-level adaptive optimization strategy. At the global level, AEGPO uses ΔEntropy to dynamically allocate rollout budgets, prioritizing prompts with higher learning value. At the local level, it exploits the peaks of Entropy(t) to guide exploration selectively at critical high-dispersion timesteps rather than uniformly across all denoising steps. By focusing computation on the most informative samples and the most critical moments, AEGPO enables more efficient and effective policy optimization. Experiments on text-to-image generation tasks demonstrate that AEGPO significantly accelerates convergence and achieves superior alignment performance compared to standard GRPO variants.

Related papers

• The Role of Entropy in Visual Grounding: Analysis and Optimization [69.51909526456606]
  We introduce ECVGPO (Entropy Control Visual Grounding Policy Optimization), an interpretable algorithm designed for effective entropy regulation.<n> Experiments show that ECVGPO achieves broad improvements across various benchmarks and models.
  arXiv  Detail & Related papers  (2025-12-07T08:33:55Z)
• ESPO: Entropy Importance Sampling Policy Optimization [7.2000276975120014]
  Entropy Importance Sampling Policy Optimization reconciles fine-grained control with training stability.<n> ESPO decomposes sequences into groups based on predictive entropy.<n>Experiments on mathematical reasoning benchmarks demonstrate that ESPO achieves convergence and state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-11-29T14:09:38Z)
• Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation [60.04281435591454]
  CRDA (Curriculum Reinforcement-Learning Data Augmentation) is a novel framework guiding detectors to progressively master multi-domain forgery features.<n>Central to our approach is integrating reinforcement learning and causal inference.<n>Our method significantly improves detector generalizability, outperforming SOTA methods across multiple cross-domain datasets.
  arXiv  Detail & Related papers  (2025-11-10T12:45:52Z)
• G$^2$RPO: Granular GRPO for Precise Reward in Flow Models [74.21206048155669]
  We propose a novel Granular-GRPO (G$2$RPO) framework that achieves precise and comprehensive reward assessments of sampling directions.<n>We introduce a Multi-Granularity Advantage Integration module that aggregates advantages computed at multiple diffusion scales.<n>Our G$2$RPO significantly outperforms existing flow-based GRPO baselines.
  arXiv  Detail & Related papers  (2025-10-02T12:57:12Z)
• 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)
• Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning [106.68304931854038]
  Reinforcement learning with verifiable rewards (RLVR) has been widely used for enhancing the reasoning abilities of large language models (LLMs)<n>We conduct a systematic empirical analysis of the entropy-performance exchange mechanism of RLVR across different levels of granularity.<n>Our analysis reveals that, in the rising stage, entropy reduction in negative samples facilitates the learning of effective reasoning patterns.<n>In the plateau stage, learning efficiency strongly correlates with high-entropy tokens present in low-perplexity samples and those located at the end of sequences.
  arXiv  Detail & Related papers  (2025-08-04T10:08:10Z)
• Understanding the Impact of Sampling Quality in Direct Preference Optimization [4.122673728216191]
  We study how data of higher quality can be leveraged to improve performance in Direct Preference Optimization (DPO)<n>Our analyses show that both the solution space and the convergence behavior of DPO depend on the support and quality of the data-generating distribution.
  arXiv  Detail & Related papers  (2025-06-03T18:12:40Z)
• 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)
• ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization [52.5587113539404]
  We introduce a causality-aware entropy term that effectively identifies and prioritizes actions with high potential impacts for efficient exploration. Our proposed algorithm, ACE: Off-policy Actor-critic with Causality-aware Entropy regularization, demonstrates a substantial performance advantage across 29 diverse continuous control tasks.
  arXiv  Detail & Related papers  (2024-02-22T13:22:06Z)
• Adversarial Style Transfer for Robust Policy Optimization in Deep Reinforcement Learning [13.652106087606471]
  This paper proposes an algorithm that aims to improve generalization for reinforcement learning agents by removing overfitting to confounding features. A policy network updates its parameters to minimize the effect of such perturbations, thus staying robust while maximizing the expected future reward. We evaluate our approach on Procgen and Distracting Control Suite for generalization and sample efficiency.
  arXiv  Detail & Related papers  (2023-08-29T18:17:35Z)

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.