English
Related papers

Related papers: Entropy Polarity in Reinforcement Fine-Tuning: Dir…

200 papers

Training LLM agents in multi-turn environments with sparse rewards, where completing a single task requires 30+ turns of interaction within an episode, presents a fundamental challenge for reinforcement learning. We identify a critical…

Machine Learning · Computer Science 2026-02-11 Wujiang Xu , Wentian Zhao , Zhenting Wang , Yu-Jhe Li , Can Jin , Mingyu Jin , Kai Mei , Kun Wan , Dimitris N. Metaxas

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

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

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 gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative…

Machine Learning · Computer Science 2026-03-13 Aleksei Petrenko , Ben Lipkin , Kevin Chen , Erik Wijmans , Marco Cusumano-Towner , Raja Giryes , Philipp Krähenbühl

Large Reasoning Models are typically trained via reinforcement learning from verifiable rewards (RLVR). However, existing approaches adopt fixed weights for positive and negative samples, and the conclusions hardly generalize to open-ended…

Artificial Intelligence · Computer Science 2026-05-28 Yunsheng Zeng , Gen Li , Yuwei Miao , Xiandong Li , Yujin Wang , Siyu Chen , Luning Wang , Yunhao Qiao , Junfeng Wang , Jianwei Lv , Bo Yuan

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

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

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

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

Large reasoning models (LRMs) are typically trained using reinforcement learning with verifiable reward (RLVR) to enhance their reasoning abilities. In this paradigm, policies are updated using both positive and negative self-generated…

Computation and Language · Computer Science 2025-12-29 Xinyu Tang , Yuliang Zhan , Zhixun Li , Wayne Xin Zhao , Zhenduo Zhang , Zujie Wen , Zhiqiang Zhang , Jun Zhou

Reinforcement learning with verifiable rewards (RLVR), particularly Group Relative Policy Optimization (GRPO), has advanced LLM reasoning. However, GRPO suffers from three credit assignment failures: uniform token-level granularity that…

Machine Learning · Computer Science 2026-05-07 Song Yu , Li Li , Wenwen Zhao , Zhisheng Yang

Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappears, policies…

Machine Learning · Computer Science 2026-05-19 Chen Wang , Zhaochun Li , Jionghao Bai , Hexuan Deng , Ge Lan , Yue Wang

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

Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning ability of Large Language Models (LLMs), but sparse outcome rewards make token-level credit assignment difficult. We study token-level credit as a…

Machine Learning · Computer Science 2026-05-27 Yuhang He , Haodong Wu , Siyi Liu , Hongyu Ge , Hange Zhou , Keyi Wu , Zhuo Zheng , Qihong Lin , Zixin Zhong , Yongqi Zhang

Proximal Policy Optimization (PPO) has been positioned by recent literature as the canonical method for the RL part of Reinforcement Learning from Human Feedback (RLHF). PPO performs well empirically but has a heuristic motivation and…

Machine Learning · Computer Science 2026-02-10 Dipan Maity

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

Multi-Agent Proximal Policy Optimization (MAPPO) is a variant of the Proximal Policy Optimization (PPO) algorithm, specifically tailored for multi-agent reinforcement learning (MARL). MAPPO optimizes cooperative multi-agent settings by…

Machine Learning · Computer Science 2026-05-14 Changha Lee , Gyusang Cho

Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be a highly effective strategy for endowing Large Language Models (LLMs) with robust multi-step reasoning abilities. However, its design and optimizations remain tailored…

Computation and Language · Computer Science 2026-04-15 Zhenhailong Wang , Xuehang Guo , Sofia Stoica , Haiyang Xu , Hongru Wang , Hyeonjeong Ha , Xiusi Chen , Yangyi Chen , Ming Yan , Fei Huang , Heng Ji

Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy…

Machine Learning · Computer Science 2026-04-20 Xiaoyun Zhang , Xiaojian Yuan , Di Huang , Wang You , Chen Hu , Jingqing Ruan , Ai Jian , Kejiang Chen , Xing Hu
‹ Prev 1 2 3 10 Next ›