AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Text-to-Image GenerationReinforcement LearningSimilar Papers 제목 키워드 기반
Guided Adaptive Credit Assignment for Sample Efficient Policy Optimization
Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems. However, it still often suffers from sparse reward tasks, which leads to poor sample efficiency during tr…
Instruction FollowingPolicy Gradient MethodsDifficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR
Reinforcement Learning with Verifiable Rewards (RLVR) has been central to the recent success of Large Reasoning Models. However, while RLVR significantly improves single-sample accuracy, it often fails to expand the mode…
Mathematical ReasoningReinforcement LearningBAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings--where stale data from past policies are used for tra…
Reinforcement LearningHeterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature
Using entropy as a measure of heterogeneity to guide optimization has emerged as a crucial research direction in Reinforcement Learning for LLMs. However, existing methods typically treat it as a discrete filter or post-…
Reinforcement LearningMathematical ReasoningUnderstanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization
Reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning ability of large language models. However, widely used RLVR algorithms, such as GRPO, often suffer from e…
Reinforcement LearningMathematical Reasoning