English
Related papers

Related papers: Dropout Strategy in Reinforcement Learning: Limiti…

200 papers

Within the domain of large language models, reinforcement fine-tuning algorithms necessitate the generation of a complete reasoning trajectory beginning from the input query, which incurs significant computational overhead during the…

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

Proximal policy optimization (PPO) is one of the most popular state-of-the-art on-policy algorithms that has become a standard baseline in modern reinforcement learning with applications in numerous fields. Though it delivers stable…

Machine Learning · Computer Science 2025-02-25 Qisai Liu , Zhanhong Jiang , Hsin-Jung Yang , Mahsa Khosravi , Joshua R. Waite , Soumik Sarkar

We present Anchored Direct Preference Optimization (ADPO), a policy alignment method derived from first principles of KL-regularized reinforcement learning. Unlike standard approaches that treat the reference policy merely as a regularizer,…

Machine Learning · Computer Science 2026-01-13 Wang Zixian

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignment uniformly…

Machine Learning · Computer Science 2026-04-03 Gengsheng Li , Tianyu Yang , Junfeng Fang , Mingyang Song , Mao Zheng , Haiyun Guo , Dan Zhang , Jinqiao Wang , Tat-Seng Chua

Recently, test-time scaling Large Language Models (LLMs) have demonstrated exceptional reasoning capabilities across scientific and professional tasks by generating long chains-of-thought (CoT). As a crucial component for developing these…

We introduce Self-correction Relative Policy Optimization (ScRPO), a novel reinforcement learning framework designed to empower large language models with advanced mathematical reasoning capabilities through iterative self-reflection and…

Artificial Intelligence · Computer Science 2026-01-06 Lianrui Li , Dakuan Lu , Jiawei Shao , Xuelong Li

In environments with delayed observation, state augmentation by including actions within the delay window is adopted to retrieve Markovian property to enable reinforcement learning (RL). However, state-of-the-art (SOTA) RL techniques with…

Machine Learning · Computer Science 2024-10-23 Qingyuan Wu , Simon Sinong Zhan , Yixuan Wang , Yuhui Wang , Chung-Wei Lin , Chen Lv , Qi Zhu , Chao Huang

Adversarial optimization algorithms that explicitly search for flaws in agents' policies have been successfully applied to finding robust and diverse policies in multi-agent settings. However, the success of adversarial optimization has…

Artificial Intelligence · Computer Science 2025-11-13 Niklas Lauffer , Ameesh Shah , Micah Carroll , Sanjit A. Seshia , Stuart Russell , Michael Dennis

Most methods in reinforcement learning use a Policy Gradient (PG) approach to learn a parametric stochastic policy that maps states to actions. The standard approach is to implement such a mapping via a neural network (NN) whose parameters…

Machine Learning · Computer Science 2024-05-29 Sergio Rozada , Antonio G. Marques

On-policy reinforcement learning (RL) algorithms are widely used for their strong asymptotic performance and training stability, but they struggle to scale with larger batch sizes, as additional parallel environments yield redundant data…

Machine Learning · Computer Science 2025-11-13 Jianren Wang , Yifan Su , Abhinav Gupta , Deepak Pathak

Traditional language model alignment methods, such as Direct Preference Optimization (DPO), are limited by their dependence on static, pre-collected paired preference data, which hampers their adaptability and practical applicability. To…

Computation and Language · Computer Science 2024-06-03 Yueqin Yin , Zhendong Wang , Yujia Xie , Weizhu Chen , Mingyuan Zhou

Reinforcement learning has become a central paradigm for improving LLM reasoning. However, existing methods use a single policy to produce both inference responses and training optimization trajectories. The objective conflict between…

Machine Learning · Computer Science 2026-01-26 Jingchu Wang , Bingbing Xu , Yige Yuan , Bin Xie , Xiaoqian Sun , Huawei Shen

A central challenge to applying many off-policy reinforcement learning algorithms to real world problems is the variance introduced by importance sampling. In off-policy learning, the agent learns about a different policy than the one being…

Machine Learning · Computer Science 2022-06-20 Eric Graves , Sina Ghiassian

Recent advancements in post-training methodologies for large language models (LLMs) have highlighted reinforcement learning (RL) as a critical component for enhancing reasoning. However, the substantial computational costs associated with…

Computation and Language · Computer Science 2025-07-29 Songjun Tu , Jiahao Lin , Xiangyu Tian , Qichao Zhang , Linjing Li , Yuqian Fu , Nan Xu , Wei He , Xiangyuan Lan , Dongmei Jiang , Dongbin Zhao

Large Reasoning Models (LRMs) achieve explicit chain-of-thought expansion by imitating deep thinking behaviors of humans, demonstrating excellent performance in complex task scenarios. However, the deep-thinking mode often leads to…

Machine Learning · Computer Science 2026-01-30 Qian Wan , Ziao Xu , Luona Wei , Xiaoxuan Shen , Jianwen Sun

Group-Relative Policy Optimization (GRPO) has emerged as the standard for training reasoning capabilities in large language models through reinforcement learning. By estimating advantages using group-mean rewards rather than a learned…

Artificial Intelligence · Computer Science 2026-03-06 Anisha Garg , Claire Zhang , Nishit Neema , David Bick , Ganesh Venkatesh , Joel Hestness

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

On-policy reinforcement learning methods like GRPO suffer from mode collapse: they exhibit reduced solution diversity, concentrating probability mass on a single solution once discovered and ceasing exploration of alternative strategies. We…

Artificial Intelligence · Computer Science 2026-05-20 Xiaozhe Li , Yang Li , Xinyu Fang , Shengyuan Ding , Peiji Li , Yongkang Chen , Yichuan Ma , Tianyi Lyu , Linyang Li , Dahua Lin , Qipeng Guo , Qingwen Liu , Kai Chen

Policy-based Reinforcement Learning (RL) has established itself as the dominant paradigm in generative recommendation for optimizing sequential user interactions. However, when applied to offline historical logs, these methods suffer a…

Machine Learning · Computer Science 2026-02-12 Jie Jiang , Yusen Huo , Xiangxin Zhan , Changping Wang , Jun Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›