中文
相关论文

相关论文: Towards Efficient and Expressive Offline RL via Fl…

200 篇论文

We present flow Q-learning (FQL), a simple and performant offline reinforcement learning (RL) method that leverages an expressive flow-matching policy to model arbitrarily complex action distributions in data. Training a flow policy with RL…

机器学习 · 计算机科学 2025-05-27 Seohong Park , Qiyang Li , Sergey Levine

Generative models have recently demonstrated remarkable success across diverse domains, motivating their adoption as expressive policies in reinforcement learning (RL). While they have shown strong performance in offline RL, particularly…

机器学习 · 计算机科学 2026-02-23 Yongjae Shin , Jongseong Chae , Jongeui Park , Youngchul Sung

Offline reinforcement learning (RL) aims to learn optimal policies from previously collected datasets. Recently, due to their powerful representational capabilities, diffusion models have shown significant potential as policy models for…

机器学习 · 计算机科学 2024-05-30 Tianle Zhang , Jiayi Guan , Lin Zhao , Yihang Li , Dongjiang Li , Zecui Zeng , Lei Sun , Yue Chen , Xuelong Wei , Lusong Li , Xiaodong He

We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast…

机器学习 · 计算机科学 2025-11-18 Zeyuan Wang , Da Li , Yulin Chen , Ye Shi , Liang Bai , Tianyuan Yu , Yanwei Fu

Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions from offline data. These algorithms build on standard policy…

机器学习 · 计算机科学 2026-02-04 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

Offline reinforcement learning (RL) optimizes a policy using only a fixed dataset, making it a practical approach in scenarios where interaction with the environment is costly. Due to this limitation, generalization ability is key to…

机器学习 · 计算机科学 2025-07-04 JunHyeok Oh , Byung-Jun Lee

This paper proposes a new design method for a stochastic control policy using a normalizing flow (NF). In reinforcement learning (RL), the policy is usually modeled as a distribution model with trainable parameters. When this…

机器人学 · 计算机科学 2024-12-18 Taisuke Kobayashi , Takumi Aotani

We present \textbf{FlowRL}, a novel framework for online reinforcement learning that integrates flow-based policy representation with Wasserstein-2-regularized optimization. We argue that in addition to training signals, enhancing the…

机器学习 · 计算机科学 2025-06-17 Lei Lv , Yunfei Li , Yu Luo , Fuchun Sun , Tao Kong , Jiafeng Xu , Xiao Ma

The dataset distributions in offline reinforcement learning (RL) often exhibit complex and multi-modal distributions, necessitating expressive policies to capture such distributions beyond widely-used Gaussian policies. To handle such…

机器学习 · 计算机科学 2026-02-23 Jongseong Chae , Jongeui Park , Yongjae Shin , Gyeongmin Kim , Seungyul Han , Youngchul Sung

Offline reinforcement learning (RL) holds promise as a means to learn high-reward policies from a static dataset, without the need for further environment interactions. However, a key challenge in offline RL lies in effectively stitching…

机器学习 · 计算机科学 2023-09-14 Siddarth Venkatraman , Shivesh Khaitan , Ravi Tej Akella , John Dolan , Jeff Schneider , Glen Berseth

Offline reinforcement learning often relies on behavior regularization that enforces policies to remain close to the dataset distribution. However, such approaches fail to distinguish between high-value and low-value actions in their…

There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity. However, effectively leveraging this expressivity for value maximization remains…

机器学习 · 计算机科学 2026-05-14 JaeHyeok Doo , Byeongguk Jeon , Seonghyeon Ye , Kimin Lee , Minjoon Seo

Generative policies based on expressive model classes, such as diffusion and flow matching, are well-suited to complex control problems with highly multimodal action distributions. Their expressivity, however, comes at a significant…

机器学习 · 计算机科学 2026-05-13 Christos Ziakas , Alessandra Russo , Avishek Joey Bose

We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm that tackles a long-standing challenge in continuous-action RL: efficient optimization of an expressive diffusion or flow-matching…

机器学习 · 计算机科学 2026-05-20 Qiyang Li , Sergey Levine

Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. Despite recent advances in hierarchical architectures such as…

机器学习 · 计算机科学 2026-04-13 Zhiqiang Dong , Teng Pang , Rongjian Xu , Guoqiang Wu

Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously collected static dataset, is an important paradigm of RL. Standard RL methods often perform poorly in this regime due to the function…

机器学习 · 计算机科学 2023-08-29 Zhendong Wang , Jonathan J Hunt , Mingyuan Zhou

Offline reinforcement learning (RL) provides a compelling paradigm for training autonomous systems without the risks of online exploration, particularly in safety-critical domains. However, jointly achieving strong safety and performance…

机器学习 · 计算机科学 2026-02-10 Manan Tayal , Mumuksh Tayal

Offline reinforcement learning (RL) aims to learn the optimal policy from a fixed dataset generated by behavior policies without additional environment interactions. One common challenge that arises in this setting is the…

机器学习 · 计算机科学 2026-02-06 Songyuan Zhang , Oswin So , H. M. Sabbir Ahmad , Eric Yang Yu , Matthew Cleaveland , Mitchell Black , Chuchu Fan

Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applicability remains largely confined to continuous action spaces. To address a broader range of…

机器学习 · 计算机科学 2026-05-14 Fairoz Nower Khan , Nabuat Zaman Nahim , Ruiquan Huang , Haibo Yang , Peizhong Ju

Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. However, despite its behavioral cloning expressiveness, FM-based…

机器学习 · 计算机科学 2025-10-14 Zhenglin Wan , Jingxuan Wu , Xingrui Yu , Chubin Zhang , Mingcong Lei , Bo An , Ivor Tsang
‹ 上一页 1 2 3 10 下一页 ›