English
Related papers

Related papers: Learning Task-relevant Representations for General…

200 papers

We study the problem of representational transfer in RL, where an agent first pretrains in a number of source tasks to discover a shared representation, which is subsequently used to learn a good policy in a \emph{target task}. We propose a…

Machine Learning · Computer Science 2023-02-23 Alekh Agarwal , Yuda Song , Wen Sun , Kaiwen Wang , Mengdi Wang , Xuezhou Zhang

Recent work has shown that representation learning plays a critical role in sample-efficient reinforcement learning (RL) from pixels. Unfortunately, in real-world scenarios, representation learning is usually fragile to task-irrelevant…

Machine Learning · Computer Science 2023-02-27 Qiyuan Liu , Qi Zhou , Rui Yang , Jie Wang

General-purpose robotic manipulation, including reach and grasp, is essential for deployment into households and workspaces involving diverse and evolving tasks. Recent advances propose using large pre-trained models, such as Large Language…

Robotics · Computer Science 2025-07-16 Huiyi Wang , Fahim Shahriar , Alireza Azimi , Gautham Vasan , Rupam Mahmood , Colin Bellinger

Reward shaping is one of the most effective methods to tackle the crucial yet challenging problem of credit assignment in Reinforcement Learning (RL). However, designing shaping functions usually requires much expert knowledge and…

Machine Learning · Computer Science 2019-01-29 Haosheng Zou , Tongzheng Ren , Dong Yan , Hang Su , Jun Zhu

Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample…

Artificial Intelligence · Computer Science 2024-04-04 Yash Shukla , Tanushree Burman , Abhishek Kulkarni , Robert Wright , Alvaro Velasquez , Jivko Sinapov

Vision-based reinforcement learning requires efficient and robust representations of image-based observations, especially when the images contain distracting (task-irrelevant) elements such as shadows, clouds, and light. It becomes more…

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

A primary challenge for visual-based Reinforcement Learning (RL) is to generalize effectively across unseen environments. Although previous studies have explored different auxiliary tasks to enhance generalization, few adopt image…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Di Zhang , Bowen Lv , Hai Zhang , Feifan Yang , Junqiao Zhao , Hang Yu , Chang Huang , Hongtu Zhou , Chen Ye , Changjun Jiang

In principle, meta-reinforcement learning algorithms leverage experience across many tasks to learn fast reinforcement learning (RL) strategies that transfer to similar tasks. However, current meta-RL approaches rely on manually-defined…

Artificial Intelligence · Computer Science 2019-12-10 Allan Jabri , Kyle Hsu , Ben Eysenbach , Abhishek Gupta , Sergey Levine , Chelsea Finn

In supervised deep learning, learning good representations for remote--sensing images (RSI) relies on manual annotations. However, in the area of remote sensing, it is hard to obtain huge amounts of labeled data. Recently, self--supervised…

Machine Learning · Computer Science 2022-09-27 Qinglin Li , Bin Li , Jonathan M Garibaldi , Guoping Qiu

Residual learning has recently surfaced as an effective means of constructing very deep neural networks for object recognition. However, current incarnations of residual networks do not allow for the modeling and integration of complex…

Computer Vision and Pattern Recognition · Computer Science 2016-07-21 Brendan Jou , Shih-Fu Chang

Learning visual representations is foundational for a broad spectrum of downstream tasks. Although recent vision-language contrastive models, such as CLIP and SigLIP, have achieved impressive zero-shot performance via large-scale…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Yin Xie , Kaicheng Yang , Xiang An , Kun Wu , Yongle Zhao , Weimo Deng , Zimin Ran , Yumeng Wang , Ziyong Feng , Roy Miles , Ismail Elezi , Jiankang Deng

Convolutional Neural Networks (CNN) conduct image classification by activating dominant features that correlated with labels. When the training and testing data are under similar distributions, their dominant features are similar, which…

Computer Vision and Pattern Recognition · Computer Science 2020-07-08 Zeyi Huang , Haohan Wang , Eric P. Xing , Dong Huang

We describe an approach to learning rich representations for images, that enables simple and effective predictors in a range of vision tasks involving spatially structured maps. Our key idea is to map small image elements to feature…

Computer Vision and Pattern Recognition · Computer Science 2019-09-02 Mohammadreza Mostajabi

Multi-goal reinforcement learning (RL) aims to qualify the agent to accomplish multi-goal tasks, which is of great importance in learning scalable robotic manipulation skills. However, reward engineering always requires strenuous efforts in…

Robotics · Computer Science 2021-09-27 Deyu Yang , Hanbo Zhang , Xuguang Lan , Jishiyu Ding

Developing personal robots that can perform a diverse range of manipulation tasks in unstructured environments necessitates solving several challenges for robotic grasping systems. We take a step towards this broader goal by presenting the…

Reinforcement Learning with Rubric Rewards (RLRR) is a framework that extends conventional reinforcement learning from human feedback (RLHF) and verifiable rewards (RLVR) by replacing scalar preference signals with structured,…

Machine Learning · Computer Science 2026-05-08 Guangchen Lan , Lian Xiong , Xin Zhou , Hejie Cui , Yuwei Zhang , Mao Li , Zhenyu Shi , Besnik Fetahu , Lihong Li , Xian Li

Image-based reinforcement learning (RL) faces significant challenges in generalization when the visual environment undergoes substantial changes between training and deployment. Under such circumstances, learned policies may not perform…

Robotics · Computer Science 2024-07-25 Weiyao Wang , Xinyuan Fang , Gregory D. Hager

The ability to autonomously learn behaviors via direct interactions in uninstrumented environments can lead to generalist robots capable of enhancing productivity or providing care in unstructured settings like homes. Such uninstrumented…

Robotics · Computer Science 2021-11-15 Rutav Shah , Vikash Kumar

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a…

Machine Learning · Computer Science 2020-06-30 Kimin Lee , Younggyo Seo , Seunghyun Lee , Honglak Lee , Jinwoo Shin

Sparse-reward reinforcement learning (RL) can model a wide range of highly complex tasks. Solving sparse-reward tasks is RL's core premise, requiring efficient exploration coupled with long-horizon credit assignment, and overcoming these…

Machine Learning · Computer Science 2025-10-21 Leander Diaz-Bone , Marco Bagatella , Jonas Hübotter , Andreas Krause