English
Related papers

Related papers: Physics-Based Motion Imitation with Adversarial Di…

200 papers

Heavy ball momentum is crucial in accelerating (stochastic) gradient-based optimization algorithms for machine learning. Existing heavy ball momentum is usually weighted by a uniform hyperparameter, which relies on excessive tuning.…

Machine Learning · Computer Science 2021-10-19 Tao Sun , Huaming Ling , Zuoqiang Shi , Dongsheng Li , Bao Wang

Moving target defense (MTD) is a proactive defense approach that aims to thwart attacks by continuously changing the attack surface of a system (e.g., changing host or network configurations), thereby increasing the adversary's uncertainty…

Cryptography and Security · Computer Science 2020-08-21 Taha Eghtesad , Yevgeniy Vorobeychik , Aron Laszka

While existing work in robust deep learning has focused on small pixel-level norm-based perturbations, this may not account for perturbations encountered in several real-world settings. In many such cases although test data might not be…

Computer Vision and Pattern Recognition · Computer Science 2021-04-09 Tejas Gokhale , Rushil Anirudh , Bhavya Kailkhura , Jayaraman J. Thiagarajan , Chitta Baral , Yezhou Yang

Reward modeling has emerged as a promising approach for the scalable alignment of language models. However, contemporary reward models (RMs) often lack robustness, awarding high rewards to low-quality, out-of-distribution (OOD) samples.…

The rise of computer vision applications in the real world puts the security of the deep neural networks at risk. Recent works demonstrate that convolutional neural networks are susceptible to adversarial examples - where the input images…

Computer Vision and Pattern Recognition · Computer Science 2024-08-22 Sina Hajer Ahmadi , Hassan Bahrami

Dexterous manipulation tasks usually have multiple objectives, and the priorities of these objectives may vary at different phases of a manipulation task. Varying priority makes a robot hardly or even failed to learn an optimal policy with…

Robotics · Computer Science 2023-09-15 Lingfeng Tao , Jiucai Zhang , Xiaoli Zhang

Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Yunhe Gao , Zhiqiang Tang , Mu Zhou , Dimitris Metaxas

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard…

While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine-tuning performance by maintaining knowledge of the source…

Machine Learning · Computer Science 2024-03-18 Shin'ya Yamaguchi , Sekitoshi Kanai , Kazuki Adachi , Daiki Chijiwa

Alternating Direction Method of Multiplier (ADMM) has been a popular algorithmic framework for separable optimization problems with linear constraints. For numerical ADMM fail to exploit the particular structure of the problem at hand nor…

Computer Vision and Pattern Recognition · Computer Science 2021-09-07 Risheng Liu , Pan Mu , Jin Zhang

Domain adaptation is an active area of research driven by the growing demand for robust machine learning models that perform well on real-world data. Adversarial learning for deep neural networks (DNNs) has emerged as a promising approach…

Computer Vision and Pattern Recognition · Computer Science 2025-01-08 Eugene Choi , Julian Rodriguez , Edmund Young

Adversarial Training (AT) with Projected Gradient Descent (PGD) is an effective approach for improving the robustness of the deep neural networks. However, PGD AT has been shown to suffer from two main limitations: i) high computational…

Computer Vision and Pattern Recognition · Computer Science 2020-12-29 Ahmadreza Jeddi , Mohammad Javad Shafiee , Alexander Wong

In recent years, imitation learning has made progress in the field of robotic manipulation. However, it still faces challenges when addressing complex long-horizon tasks with deformable objects, such as high-dimensional state spaces,…

Robotics · Computer Science 2025-03-14 Wendi Chen , Han Xue , Fangyuan Zhou , Yuan Fang , Cewu Lu

In this paper, an adaptive cooperative guidance strategy for the active protection of a target spacecraft trying to evade an interceptor was developed. The target spacecraft performs evasive maneuvers, launching an active defense vehicle to…

Systems and Control · Electrical Eng. & Systems 2022-12-07 Li Zhi , Haizhao Liang , Jinze Wu , Jianying Wang , Yu Zheng

Generalizable object manipulation skills are critical for intelligent and multi-functional robots to work in real-world complex scenes. Despite the recent progress in reinforcement learning, it is still very challenging to learn a…

Robotics · Computer Science 2022-09-14 Hao Shen , Weikang Wan , He Wang

Differential dynamic programming (DDP) is a direct single shooting method for trajectory optimization. Its efficiency derives from the exploitation of temporal structure (inherent to optimal control problems) and explicit…

In recent years, deep learning based visual tracking methods have obtained great success owing to the powerful feature representation ability of Convolutional Neural Networks (CNNs). Among these methods, classification-based tracking…

Computer Vision and Pattern Recognition · Computer Science 2020-02-10 Yihan Du , Yan Yan , Si Chen , Yang Hua

We develop Upside-Down Reinforcement Learning (UDRL), a method for learning to act using only supervised learning techniques. Unlike traditional algorithms, UDRL does not use reward prediction or search for an optimal policy. Instead, it…

Machine Learning · Computer Science 2021-09-07 Rupesh Kumar Srivastava , Pranav Shyam , Filipe Mutz , Wojciech Jaśkowski , Jürgen Schmidhuber

The robotic manipulation of compliant objects is currently one of the most active problems in robotics due to its potential to automate many important applications. Despite the progress achieved by the robotics community in recent years,…

Robotics · Computer Science 2022-05-23 Jiaming Qi , Dongyu Li , Yufeng Gao , Peng Zhou , David Navarro-Alarcon

Learning various motor skills for quadrupedal robots is a challenging problem that requires careful design of task-specific mathematical models or reward descriptions. In this work, we propose to learn a single capable policy using deep…

Robotics · Computer Science 2023-03-28 Arnaud Klipfel , Nitish Sontakke , Ren Liu , Sehoon Ha