English
Related papers

Related papers: Expand and Prune: Maximizing Trajectory Diversity …

200 papers

We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…

Machine Learning · Computer Science 2017-08-29 John Schulman , Filip Wolski , Prafulla Dhariwal , Alec Radford , Oleg Klimov

On-policy reinforcement learning (RL), particularly Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), has become the dominant paradigm for fine-tuning large language models (LLMs). While policy ratio clipping…

Machine Learning · Computer Science 2026-01-08 Yu Luo , Shuo Han , Yihan Hu , Dong Li , Jianye Hao

Aligning streaming autoregressive (AR) video generators with human preferences is challenging. Existing reinforcement learning methods predominantly rely on noise-based exploration and SDE-based surrogate policies that are mismatched to the…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Ruicheng Zhang , Kaixi Cong , Jun Zhou , Zhizhou Zhong , Zunnan Xu , Shuiyang Mao , Wei Liu , Xiu Li

Group Relative Policy Optimization (GRPO) has emerged as a promising approach for improving the reasoning capabilities of large language models. However, it struggles to effectively balance the tradeoff between exploration and exploitation…

Computation and Language · Computer Science 2026-05-13 Cheng Wang , Qin Liu , Wenxuan Zhou , Muhao Chen

Chain-of-thought (CoT) reasoning in large language models (LLMs) can be formalized as a latent variable problem, where the model needs to generate intermediate reasoning steps. While prior approaches such as iterative reward-ranked…

Machine Learning · Computer Science 2025-05-06 Jiarui Yao , Yifan Hao , Hanning Zhang , Hanze Dong , Wei Xiong , Nan Jiang , Tong Zhang

Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity. While reinforcement learning (RL) has been used to…

Machine Learning · Computer Science 2026-03-25 Orhun Buğra Baran , Melih Kandemir , Ramazan Gokberk Cinbis

Optimal Power Flow (OPF) is a very traditional research area within the power systems field that seeks for the optimal operation point of electric power plants, and which needs to be solved every few minutes in real-world scenarios.…

Artificial Intelligence · Computer Science 2025-11-25 Ángela López-Cardona , Guillermo Bernárdez , Pere Barlet-Ros , Albert Cabellos-Aparicio

The evolution of Large Language Models (LLMs) has catalyzed a paradigm shift from superficial instruction following to rigorous long-horizon reasoning. While Group Relative Policy Optimization (GRPO) has emerged as a pivotal mechanism for…

Artificial Intelligence · Computer Science 2026-01-01 Xuan Xie , Xuan Wang , Wenjie Wang , Shuai Chen , Wei Lin

Existing alignment paradigms remain limited in capturing the pluralistic nature of human values. Overton Pluralism addresses this gap by generating responses with diverse perspectives from a single query. This paper introduces OP-GRPO…

Computation and Language · Computer Science 2026-02-25 Yu Fu , Seongho Son , Ilija Bogunovic

We propose Flow-GRPO, the first method to integrate online policy gradient reinforcement learning (RL) into flow matching models. Our approach uses two key strategies: (1) an ODE-to-SDE conversion that transforms a deterministic Ordinary…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Jie Liu , Gongye Liu , Jiajun Liang , Yangguang Li , Jiaheng Liu , Xintao Wang , Pengfei Wan , Di Zhang , Wanli Ouyang

Large Language Models (LLMs) have shown remarkable reasoning capabilities through Reinforcement Learning with Verifiable Rewards (RLVR) methods. However, a key limitation of existing approaches is that rewards defined at the full trajectory…

Machine Learning · Computer Science 2025-09-30 Zhicheng Yang , Zhijiang Guo , Yinya Huang , Xiaodan Liang , Yiwei Wang , Jing Tang

We propose Fuzzy Group Relative Policy Reward (FGRPR), a novel framework that integrates Group Relative Policy Optimization (GRPO) with a fuzzy reward function to enhance learning efficiency. Unlike the conventional binary 0/1 accuracy…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Zhiqiang Wang , Pengbin Feng , Yanbin Lin , Shuzhang Cai , Zongao Bian , Jinghua Yan , Xingquan Zhu

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relative Policy…

Machine Learning · Computer Science 2026-02-09 Pengyi Li , Elizaveta Goncharova , Andrey Kuznetsov , Ivan Oseledets

Large Language Models (LLMs) can self-improve through reinforcement learning, where they generate trajectories to explore and discover better solutions. However, this exploration process is computationally expensive, often forcing current…

Machine Learning · Computer Science 2025-10-01 Ziniu Li , Congliang Chen , Tianyun Yang , Tian Ding , Ruoyu Sun , Ge Zhang , Wenhao Huang , Zhi-Quan Luo

Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent discrepancy between training noise distributions and practical inference trajectories.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Jingyuan Zhu , Biaolong Chen , Le Zhang , Aixi Zhang , Hao Jiang , Pipei Huang

RLVR has enhanced the reasoning capabilities of Large Language Models (LLMs) across various tasks. However, GRPO, a representative RLVR algorithm, suffers from a critical limitation: when all responses within a group are either entirely…

Machine Learning · Computer Science 2025-09-24 Gongrui Nan , Siye Chen , Jing Huang , Mengyu Lu , Dexun Wang , Chunmei Xie , Weiqi Xiong , Xianzhou Zeng , Qixuan Zhou , Yadong Li , Xingzhong Xu

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Computation and Language · Computer Science 2025-10-13 Shi-Qi Yan , Quan Liu , Zhen-Hua Ling

Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard recipe for post-training LLMs on reasoning tasks, with Group Relative Policy Optimization (GRPO) emerging as a leading approach. However, GRPO and its variants are…

Machine Learning · Computer Science 2026-05-12 Chanakya Ekbote , Vijay Lingam , Sujay Sanghavi , Jun Huan , Behrooz Omidvar-Tehrani , Anoop Deoras , Stefano Soatto

Reinforcement learning from verifiable rewards has emerged as a powerful technique for enhancing the complex reasoning abilities of Large Language Models (LLMs). However, these methods are fundamentally constrained by the ''learning cliff''…

Computation and Language · Computer Science 2026-03-03 Xichen Zhang , Sitong Wu , Yinghao Zhu , Haoru Tan , Shaozuo Yu , Ziyi He , Jiaya Jia

In the era of exceptionally data-hungry models, careful selection of the training data is essential to mitigate the extensive costs of deep learning. Data pruning offers a solution by removing redundant or uninformative samples from the…

Machine Learning · Computer Science 2025-02-11 Artem Vysogorets , Kartik Ahuja , Julia Kempe