Comparing Action Sets: Mutual Information as a Measure of Control

Fleer S, Ritter H (2017)
In: Artificial Neural Networks and Machine Learning – ICANN 2017. Lecture Notes in Computer Science. Springer International Publishing: 68-75.

Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Sammelwerksbeitrag | Veröffentlicht | Englisch
Abstract / Bemerkung
Finding good principles to choose the actions of artificial agents like robots in the most beneficial way to optimize their control of the environment is very much in the focus of current research in the field of intelligent systems. Especially in reinforcement learning, where the agent learns through the direct interaction with the environment, a good choice of actions is essential. We propose a new approach that allows a predictive ranking of different action sets with regard to their influence on the learning performance of an artificial agent. Our approach is based on a measure of control that utilizes the concept of mutual information. To evaluate this approach, we investigate its prediction of the effectiveness of different sets of actions in “mediated interaction” scenarios. Our results indicate that the mutual information-based measure can yield useful predictions on the aptitude of action sets for the learning process.
Erscheinungsjahr
Buchtitel
Artificial Neural Networks and Machine Learning – ICANN 2017
Seite
68-75
Konferenz
26th International Conference on Artificial Neural Networks
Konferenzort
Alghero, Italy
Konferenzdatum
2017-09-11 – 2017-09-11
PUB-ID

Zitieren

Fleer S, Ritter H. Comparing Action Sets: Mutual Information as a Measure of Control. In: Artificial Neural Networks and Machine Learning – ICANN 2017. Lecture Notes in Computer Science. Springer International Publishing; 2017: 68-75.
Fleer, S., & Ritter, H. (2017). Comparing Action Sets: Mutual Information as a Measure of Control. Artificial Neural Networks and Machine Learning – ICANN 2017, Lecture Notes in Computer Science, 68-75. Springer International Publishing. doi:10.1007/978-3-319-68600-4_9
Fleer, S., and Ritter, H. (2017). “Comparing Action Sets: Mutual Information as a Measure of Control” in Artificial Neural Networks and Machine Learning – ICANN 2017 Lecture Notes in Computer Science (Springer International Publishing), 68-75.
Fleer, S., & Ritter, H., 2017. Comparing Action Sets: Mutual Information as a Measure of Control. In Artificial Neural Networks and Machine Learning – ICANN 2017. Lecture Notes in Computer Science. Springer International Publishing, pp. 68-75.
S. Fleer and H. Ritter, “Comparing Action Sets: Mutual Information as a Measure of Control”, Artificial Neural Networks and Machine Learning – ICANN 2017, Lecture Notes in Computer Science, Springer International Publishing, 2017, pp.68-75.
Fleer, S., Ritter, H.: Comparing Action Sets: Mutual Information as a Measure of Control. Artificial Neural Networks and Machine Learning – ICANN 2017. Lecture Notes in Computer Science. p. 68-75. Springer International Publishing (2017).
Fleer, Sascha, and Ritter, Helge. “Comparing Action Sets: Mutual Information as a Measure of Control”. Artificial Neural Networks and Machine Learning – ICANN 2017. Springer International Publishing, 2017. Lecture Notes in Computer Science. 68-75.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar
ISBN Suche