Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning
We introduce Entropy-Guided Sequence Weighting (EGSW), a novel approach that enhances the exploration-exploitation tradeoff by dynamically assigning weights to generated outputs based on their advantage and entropy for Reinforcement Learning-based Large Language Model fine-tuning. EGSW integrates entropy regularization with advantage-based weighting to balance policy updates, enabling efficient exploration in high-dimensional state spaces. By employing temperature-scaled softmax weighting over sequences, EGSW prioritizing high-reward, high-uncertainty steps while maintaining training stability. Although originally developed to improve Group Relative Policy Optimization (GRPO) during large language model (LLM) fine-tuning, EGSW is generalizable to other reinforcement learning (RL) algorithms and can be implemented in both step-wise and trajectory-wise settings. Empirical evaluations demonstrate that EGSW enhances GRPO reasoning ability, yielding improvements in sample efficiency. Future work will explore the application of EGSW to advanced RL methodologies.
Code (0)
등록된 구현이 없습니다.
Tasks
Efficient ExplorationLanguage ModelingLanguage ModellingLarge Language Modelreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability
Reinforcement Learning with Verifiable Rewards algorithms like GRPO have emerged as the dominant post-training paradigm for complex reasoning in LLMs, yet commonly suffer from policy entropy collapse during training. We …
Reinforcement LearningMarginalized State Distribution Entropy Regularization in Policy Optimization
Entropy regularization is used to get improved optimization performance in reinforcement learning tasks. A common form of regularization is to maximize policy entropy to avoid premature convergence and lead to more stoch…
continuous-controlContinuous ControlReinforcement LearningFrom Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
Combining Chain-of-Thought (CoT) with Reinforcement Learning (RL) improves text-to-image (T2I) generation, yet the underlying interaction between CoT's exploration and RL's optimization remains unclear. We present a syst…
Reinforcement LearningImage GenerationEntropy Regularization with Discounted Future State Distribution in Policy Gradient Methods
The policy gradient theorem is defined based on an objective with respect to the initial distribution over states. In the discounted case, this results in policies that are optimal for one distribution over initial state…
Policy Gradient MethodsMulti-head Reward Aggregation Guided by Entropy
Aligning large language models (LLMs) with safety guidelines typically involves reinforcement learning from human feedback (RLHF), relying on human-generated preference annotations. However, assigning consistent overall …
Attribute