English
Related papers

Related papers: EAPO: Entropy-Driven Adaptive Positive-Negative Sa…

200 papers

We generalize the existing principle of the maximum Shannon entropy in reinforcement learning (RL) to weighted entropy by characterizing the state-action pairs with some qualitative weights, which can be connected with prior knowledge,…

Machine Learning · Computer Science 2020-11-19 Yizhou Zhao , Song-Chun Zhu

Speculative decoding (SD) accelerates large language model (LLM) reasoning by using a small draft model to generate candidate tokens, which the target LLM either accepts directly or regenerates upon rejection. However, excessive alignment…

Computation and Language · Computer Science 2026-01-01 Tiancheng Su , Meicong Zhang , Guoxiu He

Direct data-driven design methods for the linear quadratic regulator (LQR) mainly use offline or episodic data batches, and their online adaptation has been acknowledged as an open problem. In this paper, we propose a direct adaptive method…

Optimization and Control · Mathematics 2024-10-07 Feiran Zhao , Florian Dörfler , Alessandro Chiuso , Keyou You

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

Large reasoning models (LRMs) have demonstrated strong performance on complex reasoning tasks, but often suffer from overthinking, generating redundant content regardless of task difficulty. Inspired by the dual process theory in cognitive…

Artificial Intelligence · Computer Science 2025-05-26 Xiaoxue Cheng , Junyi Li , Zhenduo Zhang , Xinyu Tang , Wayne Xin Zhao , Xinyu Kong , Zhiqiang Zhang

Reinforcement learning (RL) has emerged as a promising paradigm for inducing explicit reasoning behaviors in large language and vision-language models. However, reasoning-oriented RL post-training remains fundamentally challenging due to…

Artificial Intelligence · Computer Science 2026-05-13 Fan Yang , Rui Meng , Trudi Di Qi , Ali Ezzati , Yuxin Wen

Policy-based reinforcement learning methods suffer from the policy collapse problem. We find valued-based reinforcement learning methods with {\epsilon}-greedy mechanism are capable of enjoying three characteristics, Closed-form Diversity,…

Machine Learning · Computer Science 2021-06-03 Changnan Xiao , Haosen Shi , Jiajun Fan , Shihong Deng

Group Relative Policy Optimization (GRPO) is a promising policy-based approach for Large Language Model alignment, yet its performance is often limited by training instability and suboptimal convergence. In this paper, we identify and…

Machine Learning · Computer Science 2025-12-12 Marco Simoni , Aleksandar Fontana , Giulio Rossolini , Andrea Saracino , Paolo Mori

Reinforcement learning from human feedback (RLHF) has emerged as a reliable approach to aligning large language models (LLMs) to human preferences. Among the plethora of RLHF techniques, proximal policy optimization (PPO) is of the most…

Computation and Language · Computer Science 2023-11-06 Banghua Zhu , Hiteshi Sharma , Felipe Vieira Frujeri , Shi Dong , Chenguang Zhu , Michael I. Jordan , Jiantao Jiao

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Machine Learning · Computer Science 2025-06-05 Yaru Hao , Li Dong , Xun Wu , Shaohan Huang , Zewen Chi , Furu Wei

Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. Reinforcement learning with verifiable rewards (RLVR) is a…

Computation and Language · Computer Science 2026-05-12 Zichao Yu , Shengze Xu , Bingqing Jiang , Wenyi Zhang , Difan Zou

We examine a class of deep learning models with a tractable method to compute information-theoretic quantities. Our contributions are three-fold: (i) We show how entropies and mutual informations can be derived from heuristic statistical…

Machine Learning · Computer Science 2020-01-22 Marylou Gabrié , Andre Manoel , Clément Luneau , Jean Barbier , Nicolas Macris , Florent Krzakala , Lenka Zdeborová

Post-training techniques combined with inference-time scaling significantly enhance the reasoning and alignment capabilities of large language models (LLMs). However, a fundamental tension arises: inference-time methods benefit from diverse…

Machine Learning · Computer Science 2026-05-12 Changhao Li , Yuchen Zhuang , Chenxiao Gao , Haotian Sun , Rushi Qiang , Chao Zhang , Bo Dai

Large Reasoning Models (LRMs) often suffer from overthinking, generating unnecessarily long reasoning chains even for simple tasks. This leads to substantial computational overhead with limited performance gain, primarily due to redundant…

Artificial Intelligence · Computer Science 2026-01-13 Ruichu Cai , Haopeng Du , Qingwen Lin , Yutong Chen , Zijian Li , Boyan Xu

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

When deploying artificial agents in real-world environments where they interact with humans, it is crucial that their behavior is aligned with the values, social norms or other requirements of that environment. However, many environments…

Machine Learning · Computer Science 2023-05-05 Mattijs Baert , Pietro Mazzaglia , Sam Leroux , Pieter Simoens

Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…

Artificial Intelligence · Computer Science 2025-10-02 Yunhao Wang , Ziting Li , Shuai Chen , Tao Liu , Chao Song , Junjie Jiang , Jian Zhu , Peng Gao , Bin Qin

In this paper, we consider recent progress in estimating the average treatment effect when extreme inverse probability weights are present and focus on methods that account for a possible violation of the positivity assumption. These…

Methodology · Statistics 2022-10-26 Roland A. Matsouaka , Yunji Zhou

Reinforcement learning with verifiable rewards has shown notable effectiveness in enhancing large language models (LLMs) reasoning performance, especially in mathematics tasks. However, such improvements often come with reduced outcome…

Artificial Intelligence · Computer Science 2026-02-03 Chenyi Li , Yuan Zhang , Bo Wang , Guoqing Ma , Wei Tang , Haoyang Huang , Nan Duan

Recent advances in large language models have highlighted the critical need for precise control over model outputs through predefined constraints. While existing methods attempt to achieve this through either direct instruction-response…

Computation and Language · Computer Science 2025-03-27 Zhouhong Gu , Xingzhou Chen , Xiaoran Shi , Tao Wang , Suhang Zheng , Tianyu Li , Hongwei Feng , Yanghua Xiao
‹ Prev 1 8 9 10 Next ›