Model-based Path Integral Stochastic Control: A Bayesian Nonparametric Approach

Over the last few years, sampling-based stochastic optimal control (SOC) frameworks have shown impressive performances in reinforcement learning (RL) with applications in robotics. However, such approaches require a large amount of samples from many interactions with the physical systems. To improve...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2014-12
Hauptverfasser:	Pan, Yunpeng, Theodorou, Evangelos A, Kontitsis, Michail
Format:	Artikel
Sprache:	eng
Schlagworte:	Bayesian analysis Control tasks Efficiency Gaussian process Integrals Iterative methods Machine learning Optimal control Robotics Stochastic processes Task complexity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!