English
Related papers

Related papers: Squeeze the Soaked Sponge: Efficient Off-policy Re…

200 papers

Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of…

Machine Learning · Computer Science 2025-10-14 Mingyang Lyu , Yinqian Sun , Erliang Lin , Huangrui Li , Ruolin Chen , Feifei Zhao , Yi Zeng

A significant portion of recent research on Large Language Model (LLM) alignment focuses on developing new policy optimization methods based on Group Relative Policy Optimization (GRPO). Two prominent directions have emerged: (i) a shift…

Machine Learning · Computer Science 2026-02-27 Svetlana Glazyrina , Maksim Kryzhanovskiy , Roman Ischenko

Off-policy Reinforcement Learning (RL) holds the promise of better data efficiency as it allows sample reuse and potentially enables safe interaction with the environment. Current off-policy policy gradient methods either suffer from high…

Machine Learning · Computer Science 2021-06-09 Samuele Tosatto , João Carvalho , Jan Peters

Reinforcement Learning (RL) has emerged as a transformative approach for aligning and enhancing Large Language Models (LLMs), addressing critical challenges in instruction following, ethical alignment, and reasoning capabilities. This…

Artificial Intelligence · Computer Science 2025-07-08 Saksham Sahai Srivastava , Vaneet Aggarwal

Parameter-efficient finetuning (PEFT) methods seek to adapt large neural models via updates to a small number of weights. However, much prior interpretability work has shown that representations encode rich semantic information, suggesting…

Computation and Language · Computer Science 2024-05-24 Zhengxuan Wu , Aryaman Arora , Zheng Wang , Atticus Geiger , Dan Jurafsky , Christopher D. Manning , Christopher Potts

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling, REINFORCE, Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), Group…

Computation and Language · Computer Science 2025-10-22 Rohit Patel

Reinforcement learning with verifiable rewards has emerged as a promising paradigm for enhancing the reasoning capabilities of large language models particularly in mathematics. Current approaches in this domain present a clear trade-off:…

Computation and Language · Computer Science 2026-02-03 Batuhan K. Karaman , Aditya Rawal , Suhaila Shakiah , Mohammad Ghavamzadeh , Mingyi Hong , Arijit Biswas , Ruida Zhou

Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fragility is especially visible in large-model training, where the training and rollout…

Machine Learning · Computer Science 2026-05-13 Rasool Fakoor , Murdock Aubry , Nicholas Stranges , Alexander J. Smola

Self-play alignment has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference optimization as a two-player game. However, the regularization with respect to the reference policy, which is…

Machine Learning · Computer Science 2025-07-09 Xiaohang Tang , Sangwoong Yoon , Seongho Son , Huizhuo Yuan , Quanquan Gu , Ilija Bogunovic

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle…

Machine Learning · Computer Science 2022-10-12 Rujie Zhong , Duohan Zhang , Lukas Schäfer , Stefano V. Albrecht , Josiah P. Hanna

Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models for advanced mathematical reasoning and coding. Following the success of frontier reasoning models, recent work has demonstrated that…

Machine Learning · Computer Science 2025-08-11 Rosie Zhao , Alexandru Meterez , Sham Kakade , Cengiz Pehlevan , Samy Jelassi , Eran Malach

Offline reinforcement learning (RL) allows robots to learn from offline datasets without risky exploration. Yet, offline RL's performance often hinges on a brittle trade-off between (1) return maximization, which can push policies outside…

Robotics · Computer Science 2026-03-06 Hokyun Im , Andrey Kolobov , Jianlong Fu , Youngwoon Lee

Off-policy problems such as policy staleness and training--inference mismatch have become a major bottleneck for training stability and further exploration in LLM RL. The distribution gap between the inference and updated policies grows…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Xuanchang Zhang , Yifan Hao , Zhou Yu , Ziji Zhang , Abhinav Gullapalli , Hao Chen , Jing Huang , Tong Zhang

Recent advances in large language models (LLMs) highlight the importance of post training techniques for improving reasoning and mathematical ability. Group Relative Policy Optimization (GRPO) has shown promise in this domain by combining…

Machine Learning · Computer Science 2026-03-20 Gabriele Carrino , Andrea Sassella , Nicolo Brunello , Federico Toschi , Mark James Carman

Recent advancements in large language models (LLMs) have shown very impressive capabilities in code generation across many programming languages. However, even state-of-the-art LLMs generate programs that contains syntactic errors and fail…

Software Engineering · Computer Science 2025-11-25 David Jiahao Fu , Aryan Gupta , Aaron Councilman , David Grove , Yu-Xiong Wang , Vikram Adve

Reinforcement learning scaling enhances the reasoning capabilities of large language models, with reinforcement learning serving as the key technique to draw out complex reasoning. However, key technical details of state-of-the-art…

Machine Learning · Computer Science 2025-08-05 Xinhan Di , JoyJiaoW

Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redistributes probability mass over solutions the base model…

Computation and Language · Computer Science 2026-05-12 Ömer Faruk Akgül , Rajgopal Kannan , Willie Neiswanger , Viktor Prasanna

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

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However,…

Machine Learning · Computer Science 2025-07-17 Ziru Liu , Cheng Gong , Xinyu Fu , Yaofang Liu , Ran Chen , Shoubo Hu , Suiyun Zhang , Rui Liu , Qingfu Zhang , Dandan Tu

Large Language Models (LLMs) generate functionally correct solutions but often fall short in code efficiency, a critical bottleneck for real-world deployment. In this paper, we introduce a novel test-time iterative optimization framework to…

Software Engineering · Computer Science 2025-06-04 Mingzhe Du , Luu Anh Tuan , Yue Liu , Yuhao Qing , Dong Huang , Xinyi He , Qian Liu , Zejun Ma , See-kiong Ng