2006 | OriginalPaper | Buchkapitel
Reinforcement Learning with Echo State Networks
verfasst von : István Szita, Viktor Gyenes, András Lőrincz
Erschienen in: Artificial Neural Networks – ICANN 2006
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Function approximators are often used in reinforcement learning tasks with large or continuous state spaces. Artificial neural networks, among them recurrent neural networks are popular function approximators, especially in tasks where some kind of of memory is needed, like in real-world partially observable scenarios. However, convergence guarantees for such methods are rarely available. Here, we propose a method using a class of novel RNNs, the echo state networks. Proof of convergence to a bounded region is provided for
k
-order Markov decision processes. Runs on POMDPs were performed to test and illustrate the working of the architecture.