Mehmet D. Erbas
Embodied imitation-enhanced reinforcement learning in multi-agent systems
Erbas, Mehmet D.; Winfield, Alan F.T.; Bull, Larry
Authors
Alan Winfield Alan.Winfield@uwe.ac.uk
Professor in Robotics
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.
Citation
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
Journal Article Type | Article |
---|---|
Online Publication Date | Aug 29, 2013 |
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 |
DOI | https://doi.org/10.1177/1059712313500503 |
Keywords | embodied imitation, reinforcement q-learning, social learning, multi-agent systems |
Public URL | https://uwe-repository.worktribe.com/output/821497 |
Publisher URL | http://dx.doi.org/10.1177/1059712313500503 |
Files
Erbas_etal_ImitationEnhancedLearning.pdf
(912 Kb)
PDF
You might also like
A two teraflop swarm
(2018)
Journal Article
Experiments in artificial theory of mind: From safety to story-telling
(2018)
Journal Article
Feature and performance comparison of the V-REP, Gazebo and ARGoS robot simulators
(2018)
Journal Article
Mapping Intelligence: Requirements and Possibilities
(2018)
Book Chapter
Negative updating combined with opinion pooling in the best-of-n problem in swarm robotics
(2018)
Journal Article