Embodied imitation-enhanced reinforcement learning in multi-agent systems

Authors:
Mehmet D Erbas;Alan Ft Winfield;Larry Bull
Affiliations:
Istanbul Kemerburgaz University, Faculty of Engineering and Architecture, Istanbul, Turkey;University of the West of England, Faculty of Environment and Technology, Bristol, UK;University of the West of England, Faculty of Environment and Technology, Bristol, UK
Venue:
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Year:
2014

Citing 12
Cited 0

Technical Note: \cal Q-Learning

Machine Learning
Experiments with reinforcement learning in problems with continuous state and action spaces

Adaptive Behavior
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Practical Reinforcement Learning in Continuous Spaces

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
The correspondence problem

Imitation in animals and artifacts
Apprenticeship learning via inverse reinforcement learning

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Learning From and About Others: Towards Using Imitation to Bootstrap the Social Understanding of Others by Robots

Artificial Life
Reinforcement Learning in Continuous Time and Space

Neural Computation
Incremental learning of gestures by imitation in a humanoid robot

Proceedings of the ACM/IEEE international conference on Human-robot interaction
Accelerating reinforcement learning through implicit imitation

Journal of Artificial Intelligence Research
Learning to act using real-time dynamic programming

Artificial Intelligence
Open-hardware e-puck Linux extension board for experimental swarm robotics research

Microprocessors & Microsystems

Quantified Score

Hi-index	0.00

Visualization

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.