English
Related papers

Related papers: Extracting Latent State Representations with Linea…

200 papers

Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexible RL approaches. To…

Machine Learning · Computer Science 2024-02-19 Moritz Lange , Noah Krystiniak , Raphael C. Engelhardt , Wolfgang Konen , Laurenz Wiskott

Robust model fitting is a core algorithm in a large number of computer vision applications. Solving this problem efficiently for datasets highly contaminated with outliers is, however, still challenging due to the underlying computational…

Computer Vision and Pattern Recognition · Computer Science 2021-03-08 Giang Truong , Huu Le , David Suter , Erchuan Zhang , Syed Zulqarnain Gilani

Sequential modelling of high-dimensional data is an important problem that appears in many domains including model-based reinforcement learning and dynamics identification for control. Latent variable models applied to sequential data…

Machine Learning · Computer Science 2023-01-23 Oliver Limoyo , Trevor Ablett , Jonathan Kelly

We develop a methodology to construct low-dimensional predictive models from data sets representing essentially nonlinear (or non-linearizable) dynamical systems with a hyperbolic linear part that are subject to external forcing with…

Dynamical Systems · Mathematics 2022-04-06 Mattia Cenedese , Joar Axås , Bastian Bäuerlein , Kerstin Avila , George Haller

Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real-world applications of RL, recovering underlying latent states is crucial, particularly when sensory…

We consider the problem of forecasting complex, nonlinear space-time processes when observations provide only partial information of on the system's state. We propose a natural data-driven framework, where the system's dynamics are modelled…

Systems and Control · Computer Science 2019-03-01 Ibrahim Ayed , Emmanuel de Bézenac , Arthur Pajot , Julien Brajard , Patrick Gallinari

Reinforcement learning has achieved great success in various applications. To learn an effective policy for the agent, it usually requires a huge amount of data by interacting with the environment, which could be computational costly and…

Machine Learning · Computer Science 2020-06-16 Kun-Peng Ning , Sheng-Jun Huang

Learning long-term dynamics models is the key to understanding physical common sense. Most existing approaches on learning dynamics from visual input sidestep long-term predictions by resorting to rapid re-planning with short-term models.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Haozhi Qi , Xiaolong Wang , Deepak Pathak , Yi Ma , Jitendra Malik

Estimating the state of an environment from high-dimensional, multimodal, and noisy observations is a fundamental challenge in reinforcement learning (RL). Traditional approaches rely on probabilistic models to account for the uncertainty,…

Machine Learning · Computer Science 2026-02-13 Alfredo Reichlin , Adriano Pacciarelli , Danica Kragic , Miguel Vasco

In this paper, we introduce a data-driven modeling approach for dynamics problems with latent variables. The state-space of the proposed model includes artificial latent variables, in addition to observed variables that can be fitted to a…

Optimization and Control · Mathematics 2024-06-19 Yushuang Luo , Xiantao Li , Wenrui Hao

This work proposes an approach for latent-dynamics learning that exactly enforces physical conservation laws. The method comprises two steps. First, the method computes a low-dimensional embedding of the high-dimensional dynamical-system…

Computational Physics · Physics 2020-06-15 Kookjin Lee , Kevin Carlberg

Learning identifiable representations and models from low-level observations is helpful for an intelligent spacecraft to complete downstream tasks reliably. For temporal observations, to ensure that the data generating process is provably…

Machine Learning · Computer Science 2024-12-05 Congxi Zhang , Yongchun Xie

State abstraction has been an essential tool for dramatically improving the sample efficiency of reinforcement-learning algorithms. Indeed, by exposing and accentuating various types of latent structure within the environment, different…

Machine Learning · Computer Science 2021-06-18 Dilip Arumugam , Benjamin Van Roy

The key assumption underlying linear Markov Decision Processes (MDPs) is that the learner has access to a known feature map $\phi(x, a)$ that maps state-action pairs to $d$-dimensional vectors, and that the rewards and transitions are…

Machine Learning · Computer Science 2023-09-20 Noah Golowich , Ankur Moitra , Dhruv Rohatgi

Dynamical models underpin our ability to understand and predict the behavior of natural systems. Whether dynamical models are developed from first-principles derivations or from observational data, they are predicated on our choice of state…

Machine Learning · Computer Science 2023-01-11 Daniel Floryan , Michael D. Graham

Recently, Koopman operator theory has become a powerful tool for developing linear representations of non-linear dynamical systems. However, existing data-driven applications of Koopman operator theory, including both traditional and deep…

Machine Learning · Computer Science 2023-05-17 King Fai Yeh , Paris Flood , William Redman , Pietro Liò

Model-free reinforcement learning has recently been shown to successfully learn navigation policies from raw sensor data. In this work, we address the problem of learning driving policies for an autonomous agent in a high-fidelity…

Machine Learning · Computer Science 2019-02-12 Qadeer Khan , Torsten Schön , Patrick Wenzel

Reinforcement Learning (RL) can effectively learn complex policies. However, learning these policies often demands extensive trial-and-error interactions with the environment. In many real-world scenarios, this approach is not practical due…

Machine Learning · Computer Science 2024-02-19 Linh Le Pham Van , Hung The Tran , Sunil Gupta

In this paper, we present a novel method for achieving dexterous manipulation of complex objects, while simultaneously securing the object without the use of passive support surfaces. We posit that a key difficulty for training such…

Representations of the world environment play a crucial role in artificial intelligence. It is often inefficient to conduct reasoning and inference directly in the space of raw sensory representations, such as pixel values of images.…

Machine Learning · Computer Science 2022-04-12 Kenji Kawaguchi , Linjun Zhang , Zhun Deng