English
Related papers

Related papers: Entropy-Preserving Reinforcement Learning

200 papers

Reinforcement learning (RL) has become a powerful paradigm for optimizing large language models (LLMs) to handle complex reasoning tasks. A core challenge in this process lies in managing policy entropy, which reflects the balance between…

Machine Learning · Computer Science 2026-04-24 Zhenpeng Su , Leiyu Pan , Minxuan Lv , Yuntao Li , Wenping Hu , Fuzheng Zhang , Kun Gai , Guorui Zhou

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

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 (RL) has become a central component of post-training for large language models (LLMs), particularly for complex reasoning tasks that require stable optimization over long generation horizons. However, achieving…

Machine Learning · Computer Science 2026-02-17 Yuepeng Sheng , Yuwei Huang , Shuman Liu , Anxiang Zeng , Haibo Zhang

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…

Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their high variance often undermines training stability. Using pathwise policy gradients, i.e.…

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

This effort is focused on examining the behavior of reinforcement learning systems in personalization environments and detailing the differences in policy entropy associated with the type of learning algorithm utilized. We demonstrate that…

Machine Learning · Computer Science 2024-04-30 Anton Dereventsov , Andrew Starnes , Clayton G. Webster

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…

Large Language Models (LLMs) have made remarkable progress in enhancing step-by-step reasoning through reinforcement learning. However, the Group Relative Policy Optimization (GRPO) algorithm, which relies on sparse reward rules, often…

Artificial Intelligence · Computer Science 2025-07-30 Xingjian Zhang , Siwei Wen , Wenjun Wu , Lei Huang

Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances. In this paper, we propose Variable Entropy Policy…

Computation and Language · Computer Science 2026-03-20 Chonghan Liu , Yimin Du , Qi An , Xin He , Cunqi Zhai , Fei Tan , Weijia Lin , Xiaochun Gong , Yongchao Deng , Shousheng Jia , Xiangzheng Zhang

In recent years, deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces such as in the Atari games. Many reinforcement learning problems, however, involve…

Machine Learning · Computer Science 2018-06-05 Yiming Zhang , Quan Ho Vuong , Kenny Song , Xiao-Yue Gong , Keith W. Ross

In this effort, we consider the impact of regularization on the diversity of actions taken by policies generated from reinforcement learning agents trained using a policy gradient. Policy gradient agents are prone to entropy collapse, which…

Machine Learning · Computer Science 2023-10-10 Andrew Starnes , Anton Dereventsov , Clayton Webster

Reinforcement learning from verifiable rewards has significantly advanced the reasoning capabilities of large language models. However, Group Relative Policy Optimization (GRPO) typically assigns a uniform, sequence-level advantage to all…

Machine Learning · Computer Science 2026-04-06 Song Yu , Li Li , Wenwen Zhao , Zhisheng Yang

Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{exploration} by encouraging the selection of more stochastic policies. In this work, we analyze this claim…

Machine Learning · Computer Science 2019-06-11 Zafarali Ahmed , Nicolas Le Roux , Mohammad Norouzi , Dale Schuurmans

To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making large but safe policy changes based on a batch of experiences.…

Machine Learning · Computer Science 2023-11-13 Jared Markowitz , Edward W. Staley

Large language model post-training relies on reinforcement learning to improve model capability and alignment quality. However, the off-policy training paradigm introduces distribution shift, which often pushes the policy beyond the trust…

Machine Learning · Computer Science 2026-04-24 Zhenpeng Su , Leiyu Pan , Minxuan Lv , Tiehua Mei , Zijia Lin , Yuntao Li , Wenping Hu , Ruiming Tang , Kun Gai , Guorui Zhou

Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Jing Wang , Jiajun Liang , Jie Liu , Henglin Liu , Gongye Liu , Jun Zheng , Wanyuan Pang , Ao Ma , Zhenyu Xie , Xintao Wang , Meng Wang , Pengfei Wan , Xiaodan Liang

Policy gradient methods usually rely on entropy regularization to prevent premature convergence. However, maximizing entropy indiscriminately pushes the policy towards a uniform distribution, often overriding the reward signal if not…

Machine Learning · Computer Science 2026-03-06 Luca Serfilippi , Giorgio Franceschelli , Antonio Corradi , Mirco Musolesi

Reinforcement learning with verifiable rewards (RLVR) has recently emerged as the leading approach for enhancing the reasoning capabilities of large language models (LLMs). However, RLVR is prone to entropy collapse, where the LLM quickly…

Machine Learning · Computer Science 2025-10-01 Jaesung R. Park , Junsu Kim , Gyeongman Kim , Jinyoung Jo , Sean Choi , Jaewoong Cho , Ernest K. Ryu
‹ Prev 1 2 3 10 Next ›