Predictive state representations: a new theory for modeling dynamical systems
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
TD(λ) networks: temporal-difference networks with eligibility traces
ICML '05 Proceedings of the 22nd international conference on Machine learning
Learning predictive representations from a history
ICML '05 Proceedings of the 22nd international conference on Machine learning
Learning predictive state representations in dynamical systems without reset
ICML '05 Proceedings of the 22nd international conference on Machine learning
Observable Operator Models for Discrete Stochastic Time Series
Neural Computation
Temporal-difference networks with history
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
| Hi-index | 0.00 |
This tutorial gives a basic yet rigorous introduction to observable operator models (OOMs). OOMs are a recently discovered class of models of stochastic processes. They are mathematically simple in that they require only concepts from elementary linear algebra. The linear algebra nature gives rise to an e?cient, consistent, unbiased, constructive learning procedure for estimating models from empirical data. The tutorial describes in detail the mathematical foundations and the practical use of OOMs for identifying and predicting discrete-time, discrete-valued processes, both for output-only and input-output systems. LOCLANGUAGE:: German LOCABSTRACT:: Dies Tutorial bietet eine grundliche Einfuhrung in observable operator Modelle (OOMs). OOMs sind eine kurzlich entdeckte Klasse von Modellen stochastischer Prozesse. Sie sind mit den Mitteln der elementaren linearen Algebra darzustellen. Die Einfachheit der Darstellung fuhrt zu einem e?zienten, konsistenten, erwartungstreuen, konstruktiven Lernverfahren fur die Induktion von Modellen aus empirischen Daten. Das Tutorial beschreibt im Detail die mathematischen Grundlagen und die praktische Verwendung von OOMs fur die Identikation und die Vorhersage zeit- und wertdiskreter Prozesse, sowohl fur reine Output-Systeme (Generatoren) als auch fur Input-Output-Systeme.