English
Related papers

Related papers: Task-Relevant and Irrelevant Region-Aware Augmenta…

200 papers

Often times in imitation learning (IL), the environment we collect expert demonstrations in and the environment we want to deploy our learned policy in aren't exactly the same (e.g. demonstrations collected in simulation but deployment in…

Neural and Evolutionary Computing · Computer Science 2024-06-19 Silvia Sapora , Gokul Swamy , Chris Lu , Yee Whye Teh , Jakob Nicolaus Foerster

This paper proposes a simple but highly efficient expansion-based model for continual learning. The recent feature transformation, masking and factorization-based methods are efficient, but they grow the model only over the global or shared…

Machine Learning · Computer Science 2023-12-05 Soumya Roy , Vinay K Verma , Deepak Gupta

In this work, we evaluate the effectiveness of representation learning approaches for decision making in visually complex environments. Representation learning is essential for effective reinforcement learning (RL) from high-dimensional…

Machine Learning · Computer Science 2022-04-26 Jun Yamada , Karl Pertsch , Anisha Gunjal , Joseph J. Lim

Data-driven approaches struggle with precise manipulation; imitation learning requires many hard-to-obtain demonstrations, while reinforcement learning yields brittle, non-generalizable policies. We introduce VisuoTactile Local (ViTaL)…

Robotics · Computer Science 2025-06-17 Zifan Zhao , Siddhant Haldar , Jinda Cui , Lerrel Pinto , Raunaq Bhirangi

This study focuses on incremental learning for image classification, exploring how to reduce catastrophic forgetting of all learned knowledge when access to old data is restricted. The challenge lies in balancing plasticity (learning new…

Machine Learning · Computer Science 2026-03-12 Zhiping Zhou , Xuchen Xie , Yiqiao Qiu , Run Lin , Weishi Zheng , Ruixuan Wang

The learning inefficiency of reinforcement learning (RL) from scratch hinders its practical application towards continuous robotic tracking control, especially for high-dimensional robots. This work proposes a data-informed residual…

Systems and Control · Electrical Eng. & Systems 2024-06-10 Cong Li , Fangzhou Liu , Yongchao Wang , Martin Buss

Machine learning models are intrinsically vulnerable to domain shift between training and testing data, resulting in poor performance in novel domains. Domain generalization (DG) aims to overcome the problem by leveraging multiple source…

Computer Vision and Pattern Recognition · Computer Science 2022-10-27 Tingwei Wang , Da Li , Kaiyang Zhou , Tao Xiang , Yi-Zhe Song

It is significantly challenging to recognize daily human actions in homes due to the diversity and dynamic changes in unconstrained home environments. It spurs the need to continually adapt to various users and scenes. Fine-tuning current…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Yuanda Hu , Xing Liu , Meiying Li , Yate Ge , Xiaohua Sun , Weiwei Guo

In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of…

Robotics · Computer Science 2018-03-30 Deirdre Quillen , Eric Jang , Ofir Nachum , Chelsea Finn , Julian Ibarz , Sergey Levine

In searching for a generalizable representation of temporally extended tasks, we spot two necessary constituents: the utility needs to be non-Markovian to transfer temporal relations invariant to a probability shift, the utility also needs…

Machine Learning · Computer Science 2020-11-20 Sirui Xie , Feng Gao , Song-Chun Zhu

The introduction of the generative adversarial imitation learning (GAIL) algorithm has spurred the development of scalable imitation learning approaches using deep neural networks. Many of the algorithms that followed used a similar…

Machine Learning · Computer Science 2023-09-21 Kai Arulkumaran , Dan Ogawa Lillrank

Model-based reinforcement learning (MBRL) has been used to efficiently solve vision-based control tasks in highdimensional image observations. Although recent MBRL algorithms perform well in trained observations, they fail when faced with…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Jeongsoo Ha , Kyungsoo Kim , Yusung Kim

Model-free deep reinforcement learning (RL) has demonstrated its superiority on many complex sequential decision-making problems. However, heavy dependence on dense rewards and high sample-complexity impedes the wide adoption of these…

Machine Learning · Computer Science 2020-04-02 Zhuangdi Zhu , Kaixiang Lin , Bo Dai , Jiayu Zhou

We consider the problem of visual imitation learning without human supervision (e.g. kinesthetic teaching or teleoperation), nor access to an interactive reinforcement learning (RL) training environment. We present a geometric perspective…

Robotics · Computer Science 2020-03-06 Jun Jin , Laura Petrich , Masood Dehghan , Martin Jagersand

Autonomous urban driving navigation with complex multi-agent dynamics is under-explored due to the difficulty of learning an optimal driving policy. The traditional modular pipeline heavily relies on hand-designed rules and the…

Computer Vision and Pattern Recognition · Computer Science 2018-07-11 Xiaodan Liang , Tairui Wang , Luona Yang , Eric Xing

Imitation learning is the problem of recovering an expert policy without access to a reward signal. Behavior cloning and GAIL are two widely used methods for performing imitation learning. Behavior cloning converges in a few iterations but…

Machine Learning · Computer Science 2020-11-11 Rohit Jena , Changliu Liu , Katia Sycara

One of the key challenges in visual Reinforcement Learning (RL) is to learn policies that can generalize to unseen environments. Recently, data augmentation techniques aiming at enhancing data diversity have demonstrated proven performance…

Computer Vision and Pattern Recognition · Computer Science 2022-02-23 Zhecheng Yuan , Guozheng Ma , Yao Mu , Bo Xia , Bo Yuan , Xueqian Wang , Ping Luo , Huazhe Xu

Data augmentations are widely used in training medical image deep learning models to increase the diversity and size of sparse datasets. However, commonly used augmentation techniques can result in loss of clinically relevant information…

Image and Video Processing · Electrical Eng. & Systems 2024-04-18 Adrit Rao , Andrea Fisher , Ken Chang , John Christopher Panagides , Katherine McNamara , Joon-Young Lee , Oliver Aalami

A long-standing goal of reinforcement learning is to acquire agents that can learn on training tasks and generalize well on unseen tasks that may share a similar dynamic but with different reward functions. The ability to generalize across…

Machine Learning · Computer Science 2026-01-26 Chengyang Ying , Xinning Zhou , Zhongkai Hao , Hang Su , Songming Liu , Dong Yan , Jun Zhu

Domain-Incremental Learning (DIL) involves the progressive adaptation of a model to new concepts across different domains. While recent advances in pre-trained models provide a solid foundation for DIL, learning new concepts often results…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Da-Wei Zhou , Zi-Wen Cai , Han-Jia Ye , Lijun Zhang , De-Chuan Zhan
‹ Prev 1 3 4 5 6 7 10 Next ›