English
Related papers

Related papers: On Entropy Control in LLM-RL Algorithms

200 papers

Despite the many recent advances in reinforcement learning (RL), the question of learning policies that robustly satisfy state constraints under unknown disturbances remains open. In this paper, we offer a new perspective on achieving…

Machine Learning · Computer Science 2025-12-23 Pierre-François Massiani , Alexander von Rohr , Lukas Haverbeck , Sebastian Trimpe

This work uses the entropy-regularised relaxed stochastic control perspective as a principled framework for designing reinforcement learning (RL) algorithms. Herein agent interacts with the environment by generating noisy controls…

Machine Learning · Computer Science 2023-09-18 Lukasz Szpruch , Tanut Treetanthiploet , Yufei Zhang

This paper aims to overcome a major obstacle in scaling RL for reasoning with LLMs, namely the collapse of policy entropy. Such phenomenon is consistently observed across vast RL runs without entropy intervention, where the policy entropy…

Policy entropy has emerged as a fundamental measure for understanding and controlling exploration in reinforcement learning with verifiable rewards (RLVR) for LLMs. However, existing entropy-aware methods mainly regulate entropy through…

Entropy Regularisation is a widely adopted technique that enhances policy optimisation performance and stability. A notable form of entropy regularisation is augmenting the objective with an entropy term, thereby simultaneously optimising…

Machine Learning · Computer Science 2024-07-26 Jean Seong Bjorn Choe , Jong-Kook Kim

Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. Traditional approaches often depend on meticulously designed prompts, high-quality examples, or additional reward models for…

Machine Learning · Computer Science 2024-06-07 Muning Wen , Junwei Liao , Cheng Deng , Jun Wang , Weinan Zhang , Ying Wen

Entropy minimization (EM) trains the model to concentrate even more probability mass on its most confident outputs. We show that this simple objective alone, without any labeled data, can substantially improve large language models' (LLMs)…

Machine Learning · Computer Science 2025-05-22 Shivam Agarwal , Zimin Zhang , Lifan Yuan , Jiawei Han , Hao Peng

We propose ERA, a new paradigm that constrains the sampling entropy above given thresholds by applying specially designed activations to the outputs of models. Our approach demonstrates broad effectiveness across different domains: 1) for…

Machine Learning · Computer Science 2025-10-13 Zilin Kang , Chonghua Liao , Tingqiang Xu , Huazhe Xu

Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of large language models (LLMs), but it often suffers from \textit{restricted exploration}, where the policy rapidly concentrates on a…

Computation and Language · Computer Science 2026-05-13 Hengrui Gu , Xiaotian Han , Yujing Bian , Feiyi Wang , Kaixiong Zhou

Entropic regularization of policies in Reinforcement Learning (RL) is a commonly used heuristic to ensure that the learned policy explores the state-space sufficiently before overfitting to a local optimal policy. The primary motivation for…

Machine Learning · Computer Science 2021-01-19 Hisham Husain , Kamil Ciosek , Ryota Tomioka

Deep Reinforcement Learning (Deep RL) has been receiving increasingly more attention thanks to its encouraging performance on a variety of control tasks. Yet, conventional regularization techniques in training neural networks (e.g., $L_2$…

Machine Learning · Computer Science 2021-11-30 Zhuang Liu , Xuanlin Li , Bingyi Kang , Trevor Darrell

Reinforcement learning with verifiable rewards (RLVR) has shown great promise in enhancing the reasoning abilities of large reasoning models (LRMs). However, it suffers from a critical issue: entropy collapse and premature convergence.…

Machine Learning · Computer Science 2025-09-30 Yuxian Jiang , Yafu Li , Guanxu Chen , Dongrui Liu , Yu Cheng , Jing Shao

In Reinforcement Learning (RL), agents have no incentive to exhibit predictable behaviors, and are often pushed (through e.g. policy entropy regularisation) to randomise their actions in favor of exploration. This often makes it challenging…

Machine Learning · Computer Science 2025-06-04 Daniel Jarne Ornia , Giannis Delimpaltadakis , Jens Kober , Javier Alonso-Mora

State entropy regularization has empirically shown better exploration and sample complexity in reinforcement learning (RL). However, its theoretical guarantees have not been studied. In this paper, we show that state entropy regularization…

Machine Learning · Computer Science 2025-12-02 Yonatan Ashlag , Uri Koren , Mirco Mutti , Esther Derman , Pierre-Luc Bacon , Shie Mannor

The entropy regularization is inspired by information entropy from machine learning and the ideas of exploration and exploitation in reinforcement learning, which appears in the control problem to design an approximating algorithm for the…

Optimization and Control · Mathematics 2024-11-21 Ziyue Chen , Qi Zhang

The Maximum Entropy Reinforcement Learning (MaxEnt RL) framework is a leading approach for achieving efficient learning and robust performance across many RL tasks. However, MaxEnt methods have also been shown to struggle with…

Machine Learning · Computer Science 2025-06-13 Ruipeng Zhang , Ya-Chien Chang , Sicun Gao

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a critical method for enhancing the reasoning capabilities of Large Language Models (LLMs). However, continuous training often leads to policy entropy collapse,…

Machine Learning · Computer Science 2026-05-11 Kun Chen , Peng Shi , Fanfan Liu , Haibo Qiu , Zhixiong Zeng , Siqi Yang , Wenji Mao

Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy…

Artificial Intelligence · Computer Science 2026-01-19 Hongye Cao , Zhixin Bai , Ziyue Peng , Boyan Wang , Tianpei Yang , Jing Huo , Yuyao Zhang , Yang Gao

Reinforcement Learning with Verifiable Rewards (RLVR) serves as a cornerstone technique for enhancing the reasoning capabilities of Large Language Models (LLMs). However, its training is often plagued by \emph{entropy collapse}, a rapid…

Machine Learning · Computer Science 2026-04-30 Zhezheng Hao , Hong Wang , Haoyang Liu , Jian Luo , Jiarui Yu , Hande Dong , Qiang Lin , Can Wang , Jiawei Chen

We consider a general multi-armed bandit problem with correlated (and simple contextual and restless) elements, as a relaxed control problem. By introducing an entropy regularisation, we obtain a smooth asymptotic approximation to the value…

Optimization and Control · Mathematics 2022-09-07 Samuel N. Cohen , Tanut Treetanthiploet