Local Gaussian Process Regression for Real Time Online Model Learning

By Duy Nguyen-Tuong, Matthias W. Seeger, Jan Peters. 2008

280 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

In Robotics & Control

Citations in the corpus

Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models (2018, background): “…such as Gaussian processes (GPs), are often the model of choice in MBRL, especially in low-dimensional problems where data efficiency is critical [Kocijan et al., 2004, Ko et al., 2007, Nguyen-Tuong et al., 2008, Grancharova et al., 2008, Deisenroth et al., 2014, Kamthe and Deisenroth, 2018].”
Model-Based Reinforcement Learning via Meta-Policy Optimization (2018, background): “However, like Bayesian models [6, 20, 21], their application is limited to low-dimensional domains.”
BM: An iterative algorithm to learn stable non-linear dynamical systems with Gaussian mixture models (2010, background): “The complexity of BM is however small compared to GPR, but comparable to its novel extension [13] that increases linearly in the number of data points for both training and retrieval.”
Continual Multi-task Gaussian Processes (2019, background): “For example, sequential rank-one updates of a locally trained GP were proposed in Nguyen-Tuong et al. (2008) or even label ranking of data points for an inclusion-deletion strategy in an active training set.”
Towards Motor Skill Learning for Robotics (2007, methodology): “The resulting method is called Local GPR or LGP [6] as it employs Gaussian process regression (GPR) for learning each local model i using”
Model Learning with Local Gaussian Process Regression (2009, unknown): “The applicability of the LGP for low-gain model-based tracking control and real-time learning is demonstrated on a Barrett whole arm manipulator (WAM) [7].”
When Gaussian Process Meets Big Data: A Review of Scalable GPs (2018, methodology): “[217] presented a simple and intuitive idea using local approximations.”
Partitioned Variational Inference: A unified framework encompassing federated and continual learning (2018, methodology): “An efficient strategy to accurately update the model in an online fashion is thus needed and can be used for various applications such as control [Nguyen-Tuong et al., 2009] or mapping [O’Callaghan and Ramos, 2012].”
Online Sparse Multi-Output Gaussian Process Regression and Learning (2019, methodology): “The local GP (LGP) technique [48], [49], on the other hand, partitions the streaming data into non-overlapping groups, each of which is exploited to train a separate single-output GP model.”
Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models (2011, methodology): “While nonparametric methods, such as Gaussian Process or variants on these, offer optimal regression [15], [28], they suffer from the curse of dimensionality.”
A survey of deep learning techniques for autonomous driving (2019, methodology): “In previous works, learning controllers have been introduced based on simple function approximators, such as Gaussian Process (GP) modeling [92], [93], [91], [94], or Support Vector Regression [95].”
Learning GP-BayesFilters via Gaussian process latent variable models (2009, background): “While it might be possible to collect ground truth data using accurate sensors (Ko and Fox 2008; Nguyen-Tuong et al. 2008; Plagemann et al. 2007) or manual labeling (Ferris et al.”
Probabilistic Differential Dynamic Programming (2014, background): “For instance, the works by Rasmussen et al.[10], Nguyen-Tuong et al.[11], Deisenroth et al.[12][13][14] and Hemakumara et al.[15] have demonstrated the remarkable applicability of GP-based control and RL methods in robotics.”