English
Related papers

Related papers: On Entropy Control in LLM-RL Algorithms

200 papers

Deep reinforcement learning (DRL) has been used to learn effective heuristics for solving complex combinatorial optimisation problem via policy networks and have demonstrated promising performance. Existing works have focused on solving…

Machine Learning · Computer Science 2020-12-25 Nasrin Sultana , Jeffrey Chan , A. K. Qin , Tabinda Sarwar

We formulate the entropy of a quantized artificial neural network as a differentiable function that can be plugged as a regularization term into the cost function minimized by gradient descent. Our formulation scales efficiently beyond the…

Machine Learning · Computer Science 2021-07-13 Enzo Tartaglione , Stéphane Lathuilière , Attilio Fiandrotti , Marco Cagnazzo , Marco Grangetto

Reinforcement Learning (RL) is a powerful tool to perform data-driven optimal control without relying on a model of the system. However, RL struggles to provide hard guarantees on the behavior of the resulting control scheme. In contrast,…

Systems and Control · Computer Science 2020-09-18 Sébastien Gros , Mario Zanon

The optimal execution problem has always been a continuously focused research issue, and many reinforcement learning (RL) algorithms have been studied. In this article, we consider the execution problem of targeting the volume weighted…

Optimization and Control · Mathematics 2024-11-12 Xingyu Zhou , Wenbin Chen , Mingyu Xu

Reinforcement Learning (RL) has shown great potential in complex control tasks, particularly when combined with deep neural networks within the Actor-Critic (AC) framework. However, in practical applications, balancing exploration, learning…

Robotics · Computer Science 2026-02-25 Zhiwei Shang , Xinyi Yuan , Wenjun Huang , Yunduan Cui , Di Chen , Meixin Zhu

We systematically explore regularizing neural networks by penalizing low entropy output distributions. We show that penalizing low entropy output distributions, which has been shown to improve exploration in reinforcement learning, acts as…

Neural and Evolutionary Computing · Computer Science 2017-01-24 Gabriel Pereyra , George Tucker , Jan Chorowski , Łukasz Kaiser , Geoffrey Hinton

This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…

Machine Learning · Computer Science 2020-08-26 Lingwei Zhu , Takamitsu Matsubara

Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depending on the environment's level of natural entropy. However,…

Machine Learning · Computer Science 2024-08-19 Adriana Hugessen , Roger Creus Castanyer , Faisal Mohamed , Glen Berseth

Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs can…

Entropy serves as a critical metric for measuring the diversity of outputs generated by large language models (LLMs), providing valuable insights into their exploration capabilities. While recent studies increasingly focus on monitoring and…

Machine Learning · Computer Science 2026-02-04 Shumin Wang , Yuexiang Xie , Wenhao Zhang , Yuchang Sun , Yanxi Chen , Yaliang Li , Yanyong Zhang

We study the sparse entropy-regularized reinforcement learning (ERL) problem in which the entropy term is a special form of the Tsallis entropy. The optimal policy of this formulation is sparse, i.e.,~at each state, it has non-zero…

Artificial Intelligence · Computer Science 2018-02-13 Ofir Nachum , Yinlam Chow , Mohammad Ghavamzadeh

Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to acquire increasingly complex reasoning and agentic behaviors. In this work, we propose two simple techniques to improve policy gradient algorithms for LLMs. First, we…

Machine Learning · Computer Science 2026-02-05 Lunjun Zhang , Jimmy Ba

The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of…

Machine Learning · Computer Science 2022-12-16 Md Masudur Rahman , Yexiang Xue

Studies on generalization performance of machine learning algorithms under the scope of information theory suggest that compressed representations can guarantee good generalization, inspiring many compression-based regularization methods.…

Machine Learning · Computer Science 2019-10-16 Antoine Saporta , Yifu Chen , Michael Blot , Matthieu Cord

Large language models (LLMs) transcend passive generation and act as goal-directed agents by invoking external tools. Reinforcement learning (RL) offers a principled framework for optimizing these emergent tool-use policies, yet the…

Computation and Language · Computer Science 2026-02-05 Zihan Lin , Xiaohan Wang , Jie Cao , Jiajun Chai , Guojun Yin , Wei Lin , Ran He

Aligning large language models (LLMs) with human preferences is essential for safe and useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct preference optimization (DPO) with human feedback for alignment.…

Computation and Language · Computer Science 2023-10-03 Tianci Xue , Ziqi Wang , Heng Ji

With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses. Prompt tuning regards selecting appropriate keywords included into the input,…

Machine Learning · Computer Science 2024-07-23 Yunseon Choi , Sangmin Bae , Seonghyun Ban , Minchan Jeong , Chuheng Zhang , Lei Song , Li Zhao , Jiang Bian , Kee-Eung Kim

Regularized reinforcement learning (RL), particularly the entropy-regularized kind, has gained traction in optimal control and inverse RL. While standard unregularized RL methods remain unaffected by changes in the number of actions, we…

Machine Learning · Computer Science 2025-01-10 Sobhan Mohammadpour , Emma Frejinger , Pierre-Luc Bacon

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 entropy collapse,…

Machine Learning · Computer Science 2026-05-13 Huimin Xu , Shuai Zhao , Xiaobao Wu , Anh Tuan Luu

Reinforcement Learning (RL) is a powerful framework to address the discrepancy between loss functions used during training and the final evaluation metrics to be used at test time. When applied to neural Machine Translation (MT), it…

Computation and Language · Computer Science 2021-02-24 Julia Ive , Zixu Wang , Marina Fomicheva , Lucia Specia