English
Related papers

Related papers: SRPO: Self-Referential Policy Optimization for Vis…

200 papers

Reinforcement learning (RL) has proven remarkably effective at improving the accuracy of language models in verifiable and deterministic domains like mathematics. Here, we examine if current RL methods are also effective at optimizing…

Machine Learning · Computer Science 2025-08-19 Michael Bereket , Jure Leskovec

Reinforcement learning (RL) has proven effective in strengthening the reasoning capabilities of large language models (LLMs). A widely adopted method, Group Relative Policy Optimization (GRPO), has shown strong empirical results in training…

Machine Learning · Computer Science 2026-03-11 Peter Chen , Xiaopeng Li , Ziniu Li , Xi Chen , Tianyi Lin

Self-supervised reinforcement learning (RL) presents a promising approach for enhancing the reasoning capabilities of Large Language Models (LLMs) without reliance on expensive human-annotated data. However, we find that existing methods…

Artificial Intelligence · Computer Science 2025-12-16 Bizhe Bai , Hongming Wu , Peng Ye , Tao Chen

Supervised fine-tuning (SFT) has become the de facto post-training strategy for large vision-language-action (VLA) models, but its reliance on costly human demonstrations limits scalability and generalization. We propose Probe, Learn,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Wenli Xiao , Haotian Lin , Andy Peng , Haoru Xue , Tairan He , Yuqi Xie , Fengyuan Hu , Jimmy Wu , Zhengyi Luo , Linxi "Jim" Fan , Guanya Shi , Yuke Zhu

Visual model-based RL methods typically encode image observations into low-dimensional representations in a manner that does not eliminate redundant information. This leaves them susceptible to spurious variations -- changes in…

Machine Learning · Computer Science 2023-10-26 Chuning Zhu , Max Simchowitz , Siri Gadipudi , Abhishek Gupta

Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capability of Large Language Models (LLMs). Current RLVR approaches typically conduct training across all generated tokens, but neglect to explore…

Computation and Language · Computer Science 2025-12-18 Yiliu Sun , Zicheng Zhao , Yang Wei , Yanfang Zhang , Chen Gong

Reinforcement learning with verifiable rewards (RLVR) has become a core post-training recipe. Introducing suitable off-policy trajectories into on-policy exploration accelerates RLVR convergence and raises the performance ceiling, yet…

Machine Learning · Computer Science 2026-04-23 Chuanyu Qin , Chenxu Yang , Qingyi Si , Naibin Gu , Dingyu Yao , Zheng Lin , Peng Fu , Nan Duan , Jiaqi Wang

Model-based offline reinforcement Learning (RL) is a promising approach that leverages existing data effectively in many real-world applications, especially those involving high-dimensional inputs like images and videos. To alleviate the…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Shenghua Wan , Ziyuan Chen , Le Gan , Shuai Feng , De-Chuan Zhan

Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may easily violate constraints that were originally satisfied…

Machine Learning · Computer Science 2024-05-06 Zhongchang Sun , Sihong He , Fei Miao , Shaofeng Zou

Recent works have demonstrated the effectiveness of reinforcement learning (RL)-based post-training for enhancing the reasoning capabilities of large language models (LLMs). In particular, Group Relative Policy Optimization (GRPO) has shown…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Jinyoung Park , Jeehye Na , Jinyoung Kim , Hyunwoo J. Kim

Reinforcement learning in large language models (LLMs) often relies on scalar rewards, a practice that discards valuable textual rationale buried in the rollouts, forcing the model to explore \textit{de novo} with each attempt and hindering…

Machine Learning · Computer Science 2025-10-21 Ang Li , Yifei Wang , Zhihang Yuan , Stefanie Jegelka , Yisen Wang

While current emotional support dialogue systems typically rely on expert-defined scalar rewards for alignment, these signals suffer from severe information sparsity. They cannot explain why a response failed or how to adapt to dynamic user…

Artificial Intelligence · Computer Science 2026-03-20 Jing Ye , Xinpei Zhao , Lu Xiang , Yaping Zhang , Chengqing Zong

End-to-end autonomous driving models based on Vision-Language-Action (VLA) architectures have shown promising results by learning driving policies through behavior cloning on expert demonstrations. However, imitation learning inherently…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Zihao Sheng , Xin Ye , Jingru Luo , Sikai Chen , Liu Ren

In batch reinforcement learning (RL), one often constrains a learned policy to be close to the behavior (data-generating) policy, e.g., by constraining the learned action distribution to differ from the behavior policy by some maximum…

Machine Learning · Computer Science 2020-03-31 Sungryull Sohn , Yinlam Chow , Jayden Ooi , Ofir Nachum , Honglak Lee , Ed Chi , Craig Boutilier

Reinforcement Learning with Verifiable Rewards (RLVR) has achieved remarkable success in improving autoregressive models, especially in domains requiring correctness like mathematical reasoning and code generation. However, directly…

Machine Learning · Computer Science 2026-03-03 Chenxing Wei , Jiazhen Kang , Hong Wang , Jianqing Zhang , Hao Jiang , Xiaolong Xu , Ningyuan Sun , Ying He , F. Richard Yu , Yao Shu , Bo Jiang

Model-based meta-reinforcement learning (RL) methods have recently been shown to be a promising approach to improving the sample efficiency of RL in multi-task settings. However, the theoretical understanding of those methods is yet to be…

Machine Learning · Computer Science 2021-10-12 Takuya Hiraoka , Takahisa Imagawa , Voot Tangkaratt , Takayuki Osa , Takashi Onishi , Yoshimasa Tsuruoka

Reinforcement learning (RL) fine-tuning has shown promise for Vision-Language-Action (VLA) models in robotic manipulation, but deployment-time visual shifts pose practical challenges. A key difficulty is that standard task rewards supervise…

Robotics · Computer Science 2026-05-14 Yuanfang Peng , Jingjing Fu , Chuheng Zhang , Li Zhao , Jiang Bian , Mingyu Liu , Ling Zhang , Jun Zhang , Rui Wang

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

Reinforcement Learning with Human Feedback (RLHF) enhances the alignment of Large Language Models (LLMs). However, its limitations have led to the development of Direct Preference Optimization (DPO), an RL-free approach designed to overcome…

Computation and Language · Computer Science 2025-02-19 Amir Saeidi , Shivanshu Verma , Aswin RRV , Kashif Rasul , Chitta Baral

On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensive data per update, leading to sample inefficiency. This paper introduces Reflective Policy…

Machine Learning · Computer Science 2024-06-07 Yaozhong Gan , Renye Yan , Zhe Wu , Junliang Xing