English
Related papers

Related papers: OP-GRPO: Efficient Off-Policy GRPO for Flow-Matchi…

200 papers

Classical on-policy algorithms such as PPO and mirror descent policy optimization provide stable proximal policy updates through tractable action likelihoods, but are typically instantiated with simple Gaussian policies whose expressiveness…

Machine Learning · Computer Science 2026-05-29 Yuehu Gong , Zeyuan Wang , Yulin Chen , Shutong Ding , Qingyuan Zhou , Yanwei Fu

Recent progress in aligning image and video generative models with Group Relative Policy Optimization (GRPO) has improved human preference alignment, but existing variants remain inefficient due to sequential rollouts and large numbers of…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Yuming Li , Yikai Wang , Yuying Zhu , Zhongyu Zhao , Ming Lu , Qi She , Shanghang Zhang

To facilitate efficient learning, policy gradient approaches to deep reinforcement learning (RL) are typically paired with variance reduction measures and strategies for making large but safe policy changes based on a batch of experiences.…

Machine Learning · Computer Science 2023-11-13 Jared Markowitz , Edward W. Staley

Few-step diffusion models enable efficient high-resolution image synthesis but struggle to align with specific downstream objectives due to limitations of existing reinforcement learning (RL) methods in low-step regimes with limited state…

Machine Learning · Computer Science 2026-03-02 Ziyi Zhang , Li Shen , Sen Zhang , Deheng Ye , Yong Luo , Miaojing Shi , Dongjing Shan , Bo Du , Dacheng Tao

Off-policy updates are inevitable in reinforcement learning (RL) for large language models (LLMs) due to rollout staleness from asynchronous training and mismatches between training and inference engines. Naive importance sampling gives an…

Machine Learning · Computer Science 2026-05-11 Guobin Shen , Chenxiao Zhao , Xiang Cheng , Lei Huang , Xing Yu

Over the several recent years, there has been a boom in development of Flow Matching (FM) methods for generative modeling. One intriguing property pursued by the community is the ability to learn flows with straight trajectories which…

Machine Learning · Statistics 2024-11-11 Nikita Kornilov , Petr Mokrov , Alexander Gasnikov , Alexander Korotin

On-policy reinforcement learning (RL) algorithms have high sample complexity while off-policy algorithms are difficult to tune. Merging the two holds the promise to develop efficient algorithms that generalize across diverse environments.…

Machine Learning · Computer Science 2019-07-17 Rasool Fakoor , Pratik Chaudhari , Alexander J. Smola

Off-policy policy optimization is a challenging problem in reinforcement learning (RL). The algorithms designed for this problem often suffer from high variance in their estimators, which results in poor sample efficiency, and have issues…

Machine Learning · Computer Science 2020-09-15 Daoming Lyu , Qi Qi , Mohammad Ghavamzadeh , Hengshuai Yao , Tianbao Yang , Bo Liu

Generative flow networks (GFlowNets) are a family of algorithms that learn a generative policy to sample discrete objects $x$ with non-negative reward $R(x)$. Learning objectives guarantee the GFlowNet samples $x$ from the target…

Machine Learning · Computer Science 2023-05-15 Max W. Shen , Emmanuel Bengio , Ehsan Hajiramezanali , Andreas Loukas , Kyunghyun Cho , Tommaso Biancalani

Reinforcement learning (RL) plays an increasingly important role in enhancing the reasoning capabilities of large language models (LLMs), yet stable and performant policy optimization remains challenging. Token-level importance ratios often…

Machine Learning · Computer Science 2025-12-02 Chang Gao , Chujie Zheng , Xiong-Hui Chen , Kai Dang , Shixuan Liu , Bowen Yu , An Yang , Shuai Bai , Jingren Zhou , Junyang Lin

Process reward models (PRMs) allow for fine-grained credit assignment in reinforcement learning (RL), and seemingly contrast with outcome reward models (ORMs), which assign a single reward to an entire trajectory. However, we provide…

Machine Learning · Computer Science 2026-05-29 Michael Sullivan , Alexander Koller

Group Relative Policy Optimization (GRPO) has become a standard approach for training mathematical reasoning models; however, its reliance on multiple completions per prompt makes training computationally expensive. Although recent work has…

Machine Learning · Computer Science 2026-01-15 Kangda Wei , Ruihong Huang

In image restoration, single-step discriminative mappings often lack fine details via expectation learning, whereas generative paradigms suffer from inefficient multi-step sampling and noise-residual coupling. To address this dilemma, we…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Zihao Fan , Xin Lu , Jie Xiao , Dong Li , Jie Huang , Xueyang Fu

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

Reinforcement learning is widely used to improve the reasoning ability of large language models, especially when answers can be automatically checked. Standard GRPO-style training updates the model using only the current step, while full…

Machine Learning · Computer Science 2026-05-11 Ismam Nur Swapnil , Aranya Saha , Tanvir Ahmed Khan , Mohammad Ariful Haque , Ser-Nam Lim

Reinforcement learning from human feedback (RLHF) shows promise for aligning diffusion and flow models, yet policy optimization methods such as GRPO suffer from inefficient and static sampling strategies. These methods treat all prompts and…

Machine Learning · Computer Science 2026-02-09 Yuming Li , Qingyu Li , Chengyu Bai , Xiangyang Luo , Zeyue Xue , Wenyu Qin , Meng Wang , Yikai Wang , Shanghang Zhang

Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training sample. However, this approach can be inefficient and yield…

Artificial Intelligence · Computer Science 2025-11-18 Yuhan Chen , Yuxuan Liu , Long Zhang , Pengzhi Gao , Jian Luan , Wei Liu

As language models become increasingly capable, users expect them to provide not only accurate responses but also behaviors aligned with diverse human preferences across a variety of scenarios. To achieve this, Reinforcement learning (RL)…

Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical limitations. (1) \textit{Shared credit assignment}:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Qiang Lyu , Zicong Chen , Chongxiao Wang , Haolin Shi , Shibo Gao , Ran Piao , Youwei Zeng , Jianlou Si , Fei Ding , Jing Li , Chun Pong Lau , Weiqiang Wang

Recently, reinforcement learning (RL) has been employed for improving generative image super-resolution (ISR) performance. However, the current efforts are focused on multi-step generative ISR, while one-step generative ISR remains…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Qiaosi Yi , Shuai Li , Rongyuan Wu , Lingchen Sun , Zhengqiang Zhang , Lei Zhang
‹ Prev 1 8 9 10 Next ›