Curiosity-driven acquisition of sensorimotor concepts using memory-based active learning

Operating in real-world environments, a robot will need to continuously learn from its experience to update and extend its knowledge. The paper focuses on the specific problem of how a robot can efficiently select information that is ldquointerestingrdquo, driving the robot's ldquocuriosityrdqu...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2008 IEEE International Conference on Robotics and Biomimetics S. 665 - 670
Hauptverfasser: Roa, S., Kruijff, G.-J.M., Jacobsson, H.
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.02.2009
Schlagworte:
Artificial intelligence
Biomimetics
developmental robotics
epigenetic robotics
Intelligent robots
interactive robot learning
Intrinsically motivated reinforcement learning
Jacobian matrices
Learning systems
Natural languages
Orbital robotics
Robot sensing systems
State estimation
State-space methods
ISBN:9781424426782, 1424426782
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Operating in real-world environments, a robot will need to continuously learn from its experience to update and extend its knowledge. The paper focuses on the specific problem of how a robot can efficiently select information that is ldquointerestingrdquo, driving the robot's ldquocuriosityrdquo. The paper investigates the hypothesis that curiosity can be emulated through a combination of active learning, and reinforcement learning using intrinsic and extrinsic rewards. Intrinsic rewards quantify learning progress, providing a measure for ldquointerestingnessrdquo of observations, and extrinsic rewards direct learning using the robot's interactions with the environment and other agents. The paper describes the approach, and experimental results obtained in simulated environments. The results indicate that both intrinsic and extrinsic rewards improve learning progress, measured in the number of training cycles to achieve a goal. The approach presented here extends previous approaches to curiosity-driven learning, by including both intrinsic and extrinsic rewards, and by considering more complex sensorimotor input.
ISBN:9781424426782
1424426782
DOI:10.1109/ROBIO.2009.4913080