Thinning-out: A Method to Reduce Trials in Skill Discovery of a Robot

In skill discovery of a robot, the number of trials (i.e., evaluations of a score function) is highly limited since each trial takes much time and cost. In this case, memory-based learning, which retains and utilizes the history of trials, is efficient. There are mainly two approaches in studies of...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Transactions of the Japanese Society for Artificial Intelligence 2009, Vol.24(1), pp.191-202
Hauptverfasser:	Kobayashi, Hayato, Hatano, Kohei, Ishino, Akira, Shinohara, Ayumi
Format:	Artikel
Sprache:	eng ; jpn
Schlagworte:	four-legged robot memory-based learning robocup skill discovery
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!