English
Related papers

Related papers: Foundation Policies with Hilbert Representations

200 papers

In the same way that generative models today conduct most of their training in a self-supervised fashion, how can agentic models conduct their training in a self-supervised fashion, interactively exploring, learning, and preparing to…

Machine Learning · Computer Science 2025-10-21 Kathryn Wantlin , Chongyi Zheng , Benjamin Eysenbach

Self-supervised reinforcement learning (RL) presents a promising approach for enhancing the reasoning capabilities of Large Language Models (LLMs) without reliance on expensive human-annotated data. However, we find that existing methods…

Artificial Intelligence · Computer Science 2025-12-16 Bizhe Bai , Hongming Wu , Peng Ye , Tao Chen

In goal-conditioned hierarchical reinforcement learning (HRL), a high-level policy specifies a subgoal for the low-level policy to reach. Effective HRL hinges on a suitable subgoal represen tation function, abstracting state space into…

Machine Learning · Computer Science 2024-06-25 Vivienne Huiling Wang , Tinghuai Wang , Wenyan Yang , Joni-Kristian Kämäräinen , Joni Pajarinen

Solving long-horizon goal-conditioned tasks remains a significant challenge in reinforcement learning (RL). Hierarchical reinforcement learning (HRL) addresses this by decomposing tasks into more manageable sub-tasks, but the automatic…

Machine Learning · Computer Science 2025-09-09 Yang Yu

Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…

Machine Learning · Computer Science 2023-10-25 Yunhai Feng , Nicklas Hansen , Ziyan Xiong , Chandramouli Rajagopalan , Xiaolong Wang

Offline reinforcement learning (RL) can be used to improve future performance by leveraging historical data. There exist many different algorithms for offline RL, and it is well recognized that these algorithms, and their hyperparameter…

Machine Learning · Computer Science 2023-01-18 Allen Nie , Yannis Flet-Berliac , Deon R. Jordan , William Steenbergen , Emma Brunskill

Sequential decision making algorithms often struggle to leverage different sources of unstructured offline interaction data. Imitation learning (IL) methods based on supervised learning are robust, but require optimal demonstrations, which…

Machine Learning · Computer Science 2023-04-28 Joey Hejna , Jensen Gao , Dorsa Sadigh

The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotations…

Computer Vision and Pattern Recognition · Computer Science 2020-07-24 Ning Wang , Wengang Zhou , Yibing Song , Chao Ma , Wei Liu , Houqiang Li

Training vision-based manipulation policies that are robust across diverse visual environments remains an important and unresolved challenge in robot learning. Current approaches often sidestep the problem by relying on invariant…

Robotics · Computer Science 2025-05-20 Sumeet Batra , Gaurav Sukhatme

Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem,…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Qiyang Li , Sergey Levine

Offline reinforcement learning (RL purely from logged data) is an important avenue for deploying RL techniques in real-world scenarios. However, existing hyperparameter selection methods for offline RL break the offline assumption by…

This paper considers the problem of learning a control policy for robot motion planning with zero-shot generalization, i.e., no data collection and policy adaptation is needed when the learned policy is deployed in new environments. We…

Systems and Control · Electrical Eng. & Systems 2024-04-09 Zhenyuan Yuan , Siyuan Xu , Minghui Zhu

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

Machine Learning · Computer Science 2018-11-29 David Warde-Farley , Tom Van de Wiele , Tejas Kulkarni , Catalin Ionescu , Steven Hansen , Volodymyr Mnih

A prominent approach to visual Reinforcement Learning (RL) is to learn an internal state representation using self-supervised methods, which has the potential benefit of improved sample-efficiency and generalization through additional…

Machine Learning · Computer Science 2023-03-16 Yanjie Ze , Nicklas Hansen , Yinbo Chen , Mohit Jain , Xiaolong Wang

We introduce a framework to leverage knowledge acquired from a repository of (heterogeneous) supervised datasets to new unsupervised datasets. Our perspective avoids the subjectivity inherent in unsupervised learning by reducing it to…

Artificial Intelligence · Computer Science 2018-02-19 Vikas K. Garg , Adam Kalai

A key challenge in scaling up robot learning to many skills and environments is removing the need for human supervision, so that robots can collect their own data and improve their own performance without being limited by the cost of…

Machine Learning · Computer Science 2017-03-14 Chelsea Finn , Sergey Levine

Offline Reinforcement Learning (RL) aims to turn large datasets into powerful decision-making engines without any online interactions with the environment. This great promise has motivated a large amount of research that hopes to replicate…

Machine Learning · Computer Science 2020-12-01 Louis Monier , Jakub Kmec , Alexandre Laterre , Thomas Pierrot , Valentin Courgeau , Olivier Sigaud , Karim Beguir

Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. Despite recent advances in hierarchical architectures such as…

Machine Learning · Computer Science 2026-04-13 Zhiqiang Dong , Teng Pang , Rongjian Xu , Guoqiang Wu

Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised…

Machine Learning · Computer Science 2019-11-01 Dushyant Rao , Francesco Visin , Andrei A. Rusu , Yee Whye Teh , Razvan Pascanu , Raia Hadsell

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

Computer Vision and Pattern Recognition · Computer Science 2017-08-22 Gustav Larsson