English
Related papers

Related papers: Generative OOD-regularized Model-based Policy Opti…

200 papers

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

Adapting large language models (LLMs) to long-context tasks requires post-training methods that remain accurate and coherent over thousands of tokens. Existing approaches are limited in several ways: 1) off-policy methods such as supervised…

Computation and Language · Computer Science 2026-05-13 Miguel Moura Ramos , Duarte M. Alves , André F. T. Martins

Offline reinforcement learning (RL) aims to find performant policies from logged data without further environment interaction. Model-based algorithms, which learn a model of the environment from the dataset and perform conservative policy…

Machine Learning · Computer Science 2022-10-12 Marc Rigter , Bruno Lacerda , Nick Hawes

Hybrid Group Relative Policy Optimization (Hybrid GRPO) is a reinforcement learning framework that extends Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) by incorporating empirical multi-sample action…

Machine Learning · Computer Science 2025-02-05 Soham Sane

The performance of Offline reinforcement learning is significantly impacted by the issue of state distributional shift, and out-of-distribution (OOD) state correction is a popular approach to address this problem. In this paper, we propose…

Machine Learning · Computer Science 2025-07-09 Ke Jiang , Wen Jiang , Xiaoyang Tan

Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative…

Machine Learning · Computer Science 2026-05-22 Zeyuan Wang , Da Li , Yulin Chen , Yuehu Gong , Yanming Guo , Ye Shi , Liang Bai , Tianyuan Yu , Yanwei Fu

Offline reinforcement learning (RL) recently gains growing interests from RL researchers. However, the performance of offline RL suffers from the out-of-distribution problem, which can be corrected by feedback in online RL. Previous offline…

Machine Learning · Computer Science 2025-06-25 Shuncheng He , Hongchang Zhang , Jianzhun Shao , Yuhang Jiang , Xiangyang Ji

Diffusion language models (DLMs) enable parallel, order-agnostic generation with iterative refinement, offering a flexible alternative to autoregressive large language models (LLMs). However, adapting reinforcement learning (RL) fine-tuning…

Machine Learning · Computer Science 2026-02-12 Kevin Rojas , Jiahe Lin , Kashif Rasul , Anderson Schneider , Yuriy Nevmyvaka , Molei Tao , Wei Deng

Offline reinforcement learning allows training reinforcement learning models on data from live deployments. However, it is limited to choosing the best combination of behaviors present in the training data. In contrast, simulation…

Machine Learning · Computer Science 2024-09-24 Eshagh Kargar , Ville Kyrki

Modern deep generative models can assign high likelihood to inputs drawn from outside the training distribution, posing threats to models in open-world deployments. While much research attention has been placed on defining new test-time…

Machine Learning · Computer Science 2022-08-22 Mu Cai , Yixuan Li

On-policy reinforcement learning (RL) algorithms are typically characterized as algorithms that perform policy updates using i.i.d. trajectories collected by the agent's current policy. However, after observing only a finite number of…

Machine Learning · Computer Science 2026-02-11 Nicholas E. Corrado , Josiah P. Hanna

We study learning optimal policies from a logged dataset, i.e., offline RL, with function approximation. Despite the efforts devoted, existing algorithms with theoretic finite-sample guarantees typically assume exploratory data coverage or…

Machine Learning · Computer Science 2023-05-25 Chenjie Mao

Offline reinforcement learning (RL) enables policy learning from pre-collected offline datasets, relaxing the need to interact directly with the environment. However, limited by the quality of offline datasets, it generally fails to learn…

Machine Learning · Computer Science 2025-09-03 Xingshuai Huang , Di Wu , Benoit Boulet

Offline reinforcement learning (RL), also known as batch RL, aims to optimize policy from a large pre-recorded dataset without interaction with the environment. This setting offers the promise of utilizing diverse, pre-collected datasets to…

Machine Learning · Computer Science 2021-01-05 Qiang He , Xinwen Hou

Offline reinforcement learning (RL) optimizes the policy on a previously collected dataset without any interactions with the environment, yet usually suffers from the distributional shift problem. To mitigate this issue, a typical solution…

Machine Learning · Computer Science 2023-09-06 Qisen Yang , Shenzhi Wang , Qihang Zhang , Gao Huang , Shiji Song

Group Relative Policy Optimization (GRPO) is a promising policy-based approach for Large Language Model alignment, yet its performance is often limited by training instability and suboptimal convergence. In this paper, we identify and…

Machine Learning · Computer Science 2025-12-12 Marco Simoni , Aleksandar Fontana , Giulio Rossolini , Andrea Saracino , Paolo Mori

Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before…

Machine Learning · Computer Science 2024-04-11 Guojian Wang , Faguo Wu , Xiao Zhang

Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two…

Machine Learning · Computer Science 2026-03-10 Jianyuan Zhong , Kaibo Wang , Ding Ding , Zijin Feng , Haoli Bai , Yang Xiang , Jiacheng Sun , Qiang Xu

Diffusion large language models (dLLMs), which offer a promising alternative to traditional autoregressive LLMs, have recently shown strong results in pretraining. However, due to their lack of tractable sequence-level likelihoods, they…

Machine Learning · Computer Science 2026-02-03 Anthony Zhan

We address the problem of fine-tuning pre-trained generative policies with reinforcement learning (RL) while preserving the multimodality of their action distributions. Existing methods for RL fine-tuning of generative policies (e.g.,…

Machine Learning · Computer Science 2026-05-13 Alberta Longhini , David Emukpere , Jean-Michel Renders , Seungsu Kim