English
Related papers

Related papers: Scaling Proprioceptive-Visual Learning with Hetero…

200 papers

Learning control from pixels is difficult for reinforcement learning (RL) agents because representation learning and policy learning are intertwined. Previous approaches remedy this issue with auxiliary representation learning tasks, but…

Machine Learning · Computer Science 2024-01-30 Trevor McInroe , Lukas Schäfer , Stefano V. Albrecht

Transformer-based large language models (LLMs) have demonstrated exceptional capabilities in sequence modeling and text generation, with improvements scaling proportionally with model size. However, the limitations of GPU memory have…

Machine Learning · Computer Science 2025-03-05 Zihao Zeng , Chubo Liu , Xin He , Juan Hu , Yong Jiang , Fei Huang , Kenli Li , Wei Yang Bryan Lim

Vision-language-action policies learn manipulation skills across tasks, environments and embodiments through large-scale pre-training. However, their ability to generalize to novel robot configurations remains limited. Most approaches…

Robotics · Computer Science 2025-09-19 Anzhe Chen , Yifei Yang , Zhenjie Zhu , Kechun Xu , Zhongxiang Zhou , Rong Xiong , Yue Wang

Scalable robot policy pre-training has been hindered by the high cost of collecting high-quality demonstrations for each platform. In this study, we address this issue by uniting offline reinforcement learning (offline RL) with…

Artificial Intelligence · Computer Science 2026-02-23 Haruki Abe , Takayuki Osa , Yusuke Mukuta , Tatsuya Harada

Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems has been relatively…

Computer Vision and Pattern Recognition · Computer Science 2021-08-13 Josh Beal , Hao-Yu Wu , Dong Huk Park , Andrew Zhai , Dmitry Kislyuk

Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning -- a key tool for performing meta-learning -- learns a…

Machine Learning · Computer Science 2022-01-04 Nilesh Tripuraneni , Chi Jin , Michael I. Jordan

Developing generalizable robot policies that can robustly handle varied environmental conditions and object instances remains a fundamental challenge in robot learning. While considerable efforts have focused on collecting large robot…

Robotics · Computer Science 2024-12-10 Mara Levy , Siddhant Haldar , Lerrel Pinto , Abhinav Shirivastava

In the field of legged robot motion control, reinforcement learning (RL) holds great promise but faces two major challenges: high computational cost for training individual robots and poor generalization of trained models. To address these…

Robotics · Computer Science 2025-04-09 Haodong Huang , Shilong Sun , Zida Zhao , Hailin Huang , Changqing Shen , Wenfu Xu

To mimic human vision with the way of recognizing the diverse and open world, foundation vision models are much critical. While recent techniques of self-supervised learning show the promising potentiality of this mission, we argue that…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Zhiming Qian

Reinforcement learning is an emerging approach to control dynamical systems for which classical approaches are difficult to apply. However, trained agents may not generalize against the variations of system parameters. This paper presents…

Systems and Control · Electrical Eng. & Systems 2023-11-10 Abdel Gafoor Haddad , Igor Boiko , Yahya Zweiri

Robotic grasping presents a difficult motor task in real-world scenarios, constituting a major hurdle to the deployment of capable robots across various industries. Notably, the scarcity of data makes grasping particularly challenging for…

Robotics · Computer Science 2024-06-18 Abhi Kamboj , Katherine Driggs-Campbell

The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot locomotion, individual skills are…

Robotics · Computer Science 2026-03-10 Jiale Fan , Andrei Cramariuc , Tifanny Portela , Marco Hutter

Offline post-training adapts a pretrained robot policy to a target dataset by supervised regression on recorded actions. In practice, robot datasets are heterogeneous: they mix embodiments, camera setups, and demonstrations of varying…

Robotics · Computer Science 2026-03-18 Wanpeng Zhang , Hao Luo , Sipeng Zheng , Yicheng Feng , Haiweng Xu , Ziheng Xi , Chaoyi Xu , Haoqi Yuan , Zongqing Lu

The ability to plan for multi-step manipulation tasks in unseen situations is crucial for future home robots. But collecting sufficient experience data for end-to-end learning is often infeasible in the real world, as deploying robots in…

Robotics · Computer Science 2022-05-18 Chen Wang , Danfei Xu , Li Fei-Fei

Imitation learning is an effective and safe technique to train robot policies in the real world because it does not depend on an expensive random exploration process. However, due to the lack of exploration, learning policies that…

Robotics · Computer Science 2021-06-24 Ajay Mandlekar , Danfei Xu , Roberto Martín-Martín , Silvio Savarese , Li Fei-Fei

Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Zhong-Yu Li , Bo-Wen Yin , Yongxiang Liu , Li Liu , Ming-Ming Cheng

Large-scale robotic policies trained on data from diverse tasks and robotic platforms hold great promise for enabling general-purpose robots; however, reliable generalization to new environment conditions remains a major challenge. Toward…

Robotics · Computer Science 2024-07-30 Bo Wu , Bruce D. Lee , Kostas Daniilidis , Bernadette Bucher , Nikolai Matni

Generalist robot policies trained on large-scale datasets such as Open X-Embodiment (OXE) demonstrate strong performance across a wide range of tasks. However, they often struggle to generalize beyond the distribution of their training…

Robotics · Computer Science 2025-08-11 Youguang Xing , Xu Luo , Junlin Xie , Lianli Gao , Hengtao Shen , Jingkuan Song

Humans are able to seamlessly visually imitate others, by inferring their intentions and using past experience to achieve the same end goal. In other words, we can parse complex semantic knowledge from raw video and efficiently translate…

Machine Learning · Computer Science 2020-11-12 Sudeep Dasari , Abhinav Gupta

A key challenge in manipulation is learning a policy that can robustly generalize to diverse visual environments. A promising mechanism for learning robust policies is to leverage video generative models, which are pretrained on large-scale…