Skip to main content

Research Repository

See what's under the surface

Embodied imitation-enhanced reinforcement learning in multi-agent systems

Winfield, Alan FT; Erbas, Mehmet D.; Winfield, Alan F.T.; Bull, Larry

Authors

Alan FT Winfield

Mehmet D. Erbas

Lawrence Bull Larry.Bull@uwe.ac.uk
AHOD Research and Scholarship and Prof



Abstract

Imitation is an example of social learning in which an individual observes and copies another's actions. This paper presents a new method for using imitation as a way of enhancing the learning speed of individual agents that employ a well-known reinforcement learning algorithm, namely Q-learning. Compared with other research that uses imitation with reinforcement learning, our method uses imitation of purely observed behaviours to enhance learning, with no internal state access or sharing of experiences between agents. The paper evaluates our imitation-enhanced reinforcement learning approach in both simulation and with real robots in continuous space. Both simulation and real robot experimental results show that the learning speed of the group is improved. © The Author(s) 2013.

Journal Article Type Article
Publication Date Feb 1, 2014
Journal Adaptive Behavior
Print ISSN 1059-7123
Electronic ISSN 1741-2633
Publisher SAGE Publications
Peer Reviewed Peer Reviewed
Volume 22
Issue 1
Pages 31-50
APA6 Citation Winfield, A. F., Erbas, M. D., Winfield, A. F., & Bull, L. (2014). Embodied imitation-enhanced reinforcement learning in multi-agent systems. Adaptive Behavior, 22(1), 31-50. https://doi.org/10.1177/1059712313500503
DOI https://doi.org/10.1177/1059712313500503
Keywords embodied imitation, reinforcement q-learning, social learning, multi-agent systems
Publisher URL http://dx.doi.org/10.1177/1059712313500503

Files







You might also like



Downloadable Citations