English
Related papers

Related papers: Controllable Flow Matching for Online Reinforcemen…

200 papers

We study behavior-regularized reinforcement learning (RL), where regularization toward a reference distribution (the dataset in offline RL or the base model in LLM RL finetuning) is essential to prevent value over-optimization caused by…

Machine Learning · Computer Science 2026-04-17 Haoran Xu , Kaiwen Hu , Somayeh Sojoudi , Amy Zhang

Unconditional flow-matching trains diffusion models to transport samples from a source distribution to a target distribution by enforcing that the flows between sample pairs are unique. However, in conditional settings (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 George Stoica , Vivek Ramanujan , Xiang Fan , Ali Farhadi , Ranjay Krishna , Judy Hoffman

Reinforcement learning (RL) has emerged as an effective paradigm for enhancing model reasoning. However, existing RL methods like GRPO typically rely on unstructured self-sampling to fit scalar rewards, often producing inefficient rollouts…

Computation and Language · Computer Science 2026-05-18 Jinyang Wu , Chonghua Liao , Mingkuan Feng , Shuai Zhang , Zhengqi Wen , Haoran Luo , Ling Yang , Huazhe Xu , Jianhua Tao

In this paper, we leverage ideas from model-based control to address the sample efficiency problem of reinforcement learning (RL) algorithms. Accelerating learning is an active field of RL highly relevant in the context of time-varying…

Systems and Control · Electrical Eng. & Systems 2023-05-23 Ibrahim Ahmed , Marcos Quinones-Grueiro , Gautam Biswas

We propose a deep reinforcement learning (DRL) methodology for the tracking, obstacle avoidance, and formation control of nonholonomic robots. By separating vision-based control into a perception module and a controller module, we can train…

Robotics · Computer Science 2019-11-19 Yanlin Zhou , Fan Lu , George Pu , Xiyao Ma , Runhan Sun , Hsi-Yuan Chen , Xiaolin Li , Dapeng Wu

Flow-based generative models provide strong unconditional priors for inverse problems, but guiding their dynamics for conditional generation remains challenging. Recent work casts training-free conditional generation in flow models as an…

Image and Video Processing · Electrical Eng. & Systems 2026-02-02 George Webber , Alexander Denker , Riccardo Barbano , Andrew J Reader

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as…

Machine Learning · Computer Science 2021-03-12 Bernie Wang , Simon Xu , Kurt Keutzer , Yang Gao , Bichen Wu

Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally…

Machine Learning · Computer Science 2023-11-09 Tianying Ji , Yu Luo , Fuchun Sun , Mingxuan Jing , Fengxiang He , Wenbing Huang

Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on…

Machine Learning · Computer Science 2026-01-19 Zhang Xiaocai , Xiao Zhe , Liang Maohan , Liu Tao , Li Haijiang , Zhang Wenbin

Online reinforcement learning (RL) excels in complex, safety-critical domains but suffers from sample inefficiency, training instability, and limited interpretability. Data attribution provides a principled way to trace model behavior back…

Machine Learning · Computer Science 2025-10-07 Yuzheng Hu , Fan Wu , Haotian Ye , David Forsyth , James Zou , Nan Jiang , Jiaqi W. Ma , Han Zhao

Recent advances in generative models have produced strong results for static 3D shapes, whereas articulated 3D generation remains challenging due to action-dependent deformations and limited datasets. We introduce ArticFlow, a two-stage…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Jiong Lin , Jinchen Ruan , Hod Lipson

Reinforcement learning (RL) in few-shot scenarios with limited sensor data is challenging due to insufficient training samples, particularly in applications like Dynamic Voltage and Frequency Scaling (DVFS) where sensor readings are…

Machine Learning · Computer Science 2026-01-13 Mohammad Pivezhandi , Abusayeed Saifullah

Deep reinforcement learning (DRL) has emerged as a powerful paradigm for solving complex decision-making problems. However, DRL-based systems still face significant dependability challenges particularly in real-time environments due to the…

Software Engineering · Computer Science 2026-03-25 Guoxin Su , Thomas Robinson , Hoa Khanh Dam , Li Liu , David S. Rosenblum

Reinforcement learning (RL) is gaining attention by more and more researchers in quantitative finance as the agent-environment interaction framework is aligned with decision making process in many business problems. Most of the current…

Mathematical Finance · Quantitative Finance 2022-05-31 Huifang Huang , Ting Gao , Yi Gui , Jin Guo , Peng Zhang

The coupling of deep reinforcement learning to numerical flow control problems has recently received a considerable attention, leading to groundbreaking results and opening new perspectives for the domain. Due to the usually high…

Machine Learning · Computer Science 2023-07-14 J. Viquerat , E. Hachem

This paper uses supervised learning, random search and deep reinforcement learning (DRL) methods to control large signalized intersection networks. The traffic model is Cellular Automaton rule 184, which has been shown to be a…

Artificial Intelligence · Computer Science 2025-04-07 Jorge A. Laval , Hao Zhou

Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL has not been very standardized. It is fairly common for…

Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization impractical.…

Machine Learning · Computer Science 2026-02-02 Lingkai Kong , Anagha Satish , Hezi Jiang , Akseli Kangaslahti , Andrew Ma , Wenbo Chen , Mingxiao Song , Lily Xu , Milind Tambe

Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 David McAllister , Miika Aittala , Tero Karras , Janne Hellsten , Angjoo Kanazawa , Timo Aila , Samuli Laine

Turbulent-flow control aims to develop strategies that effectively manipulate fluid systems, such as the reduction of drag in transportation and enhancing energy efficiency, both critical steps towards reducing global CO$_2$ emissions. Deep…

Fluid Dynamics · Physics 2026-05-25 Miguel Beneitez , Andres Cremades , Luca Guastoni , Ricardo Vinuesa
‹ Prev 1 8 9 10 Next ›