English
Related papers

Related papers: Synthetic Data is Sufficient for Zero-Shot Visual …

200 papers

Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Machine Learning · Computer Science 2021-10-05 Elie Aljalbout , Maximilian Ulmer , Rudolph Triebel

The standard approach to tackling computer vision problems is to train deep convolutional neural network (CNN) models using large-scale image datasets which are representative of the target task. However, in many scenarios, it is often…

Computer Vision and Pattern Recognition · Computer Science 2024-04-01 Alhassan Mumuni , Fuseini Mumuni , Nana Kobina Gerrar

Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online RL agents trained in imperfect simulation environments can…

Machine Learning · Computer Science 2025-04-17 Haoyi Niu , Tianying Ji , Bingqi Liu , Haocheng Zhao , Xiangyu Zhu , Jianying Zheng , Pengfei Huang , Guyue Zhou , Jianming Hu , Xianyuan Zhan

This work presents reinforcement learning (RL)-driven data augmentation to improve the generalization of vision-action (VA) models for dexterous grasping. While real-to-sim-to-real frameworks, where a few real demonstrations seed…

Robotics · Computer Science 2025-04-28 Atsushi Kanehira , Naoki Wake , Kazuhiro Sasabuchi , Jun Takamatsu , Katsushi Ikeuchi

Offline reinforcement learning (RL) aims to find optimal policies in dynamic environments in order to maximize the expected total rewards by leveraging pre-collected data. Learning from heterogeneous data is one of the fundamental…

Machine Learning · Statistics 2026-03-10 Rui Miao , Babak Shahbaba , Annie Qu

Reinforcement Learning (RL) has demonstrated remarkable success in solving sequential decision-making problems. However, in real-world scenarios, RL agents often struggle to generalize when faced with unseen actions that were not…

Machine Learning · Computer Science 2025-03-13 Abdullah Alchihabi , Hanping Zhang , Yuhong Guo

Deep research agents have shown remarkable potential in handling long-horizon tasks. However, state-of-the-art performance typically relies on online reinforcement learning (RL), which is financially expensive due to extensive API calls.…

Artificial Intelligence · Computer Science 2026-02-24 Yuhang Zhou , Kai Zheng , Qiguang Chen , Mengkang Hu , Qingfeng Sun , Can Xu , Jingjing Chen

Recently, robust reinforcement learning (RL) methods designed to handle adversarial input observations have received significant attention, motivated by RL's inherent vulnerabilities. While existing approaches have demonstrated reasonable…

Machine Learning · Computer Science 2025-06-23 Kosuke Nakanishi , Akihiro Kubo , Yuji Yasui , Shin Ishii

Offline reinforcement learning (RL) can in principle synthesize more optimal behavior from a dataset consisting only of suboptimal trials. One way that this can happen is by "stitching" together the best parts of otherwise suboptimal…

Machine Learning · Computer Science 2023-11-01 Joey Hong , Anca Dragan , Sergey Levine

A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks over a high-dimensional observation space to similar tasks…

Machine Learning · Computer Science 2022-03-17 Bogdan Mazoure , Ahmed M. Ahmed , Patrick MacAlpine , R Devon Hjelm , Andrey Kolobov

End-to-end (E2E) autonomous driving models that take only camera images as input and directly predict a future trajectory are appealing for their computational efficiency and potential for improved generalization via unified optimization;…

Robotics · Computer Science 2026-04-10 Chihiro Noguchi , Takaki Yamamoto

Offline reinforcement learning has received extensive attention from scholars because it avoids the interaction between the agent and the environment by learning a policy through a static dataset. However, general reinforcement learning…

Machine Learning · Computer Science 2026-02-12 Yi Shen , Hanyan Huang

While large models trained with self-supervised learning on offline datasets have shown remarkable capabilities in text and image domains, achieving the same generalisation for agents that act in sequential decision problems remains an open…

Machine Learning · Computer Science 2025-03-04 Michael Matthews , Michael Beukman , Chris Lu , Jakob Foerster

Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Weixing Liu , Jun Liu , Bin Luo

Generative foundation models like Stable Diffusion comprise a diverse spectrum of knowledge in computer vision with the potential for transfer learning, e.g., via generating data to train student models for downstream tasks. This could…

Computer Vision and Pattern Recognition · Computer Science 2024-05-07 Leonhard Hennicke , Christian Medeiros Adriano , Holger Giese , Jan Mathias Koehler , Lukas Schott

Reinforcement learning (RL) has achieved remarkable success in real-world decision-making across diverse domains, including gaming, robotics, online advertising, public health, and natural language processing. Despite these advances, a…

Applications · Statistics 2026-01-23 Asim H. Gazi , Yongyi Guo , Daiqi Gao , Ziping Xu , Kelly W. Zhang , Susan A. Murphy

Generative Adversarial Networks (GANs) have been used widely to generate large volumes of synthetic data. This data is being utilized for augmenting with real examples in order to train deep Convolutional Neural Networks (CNNs). Studies…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Binod Bhattarai , Seungryul Baek , Rumeysa Bodur , Tae-Kyun Kim

Robotic mobility aids for blind and low-vision (BLV) individuals rely heavily on deep learning-based vision models specialized for various navigational tasks. However, the performance of these models is often constrained by the availability…

Computer Vision and Pattern Recognition · Computer Science 2024-09-18 Hochul Hwang , Krisha Adhikari , Satya Shodhaka , Donghyun Kim

Extensive efforts have been made to improve the generalization ability of Reinforcement Learning (RL) methods via domain randomization and data augmentation. However, as more factors of variation are introduced during training, optimization…

Machine Learning · Computer Science 2021-04-12 Nicklas Hansen , Xiaolong Wang

Offline reinforcement learning (RL) aims to learn a policy using only pre-collected and fixed data. Although avoiding the time-consuming online interactions in RL, it poses challenges for out-of-distribution (OOD) state actions and often…

Machine Learning · Computer Science 2023-06-23 Jinxin Liu , Ziqi Zhang , Zhenyu Wei , Zifeng Zhuang , Yachen Kang , Sibo Gai , Donglin Wang