Concurrent modular Q-learning with local rewards on linked multi-component robotic systems

Authors:
Borja Fernandez-Gauna;Jose Manuel Lopez-Guede;Manuel Graña
Affiliations:
University of the Basque Country(UPV/EHU);University of the Basque Country(UPV/EHU);University of the Basque Country(UPV/EHU)
Venue:
IWINAC'11 Proceedings of the 4th international conference on Interplay between natural and artificial computation - Volume Part I
Year:
2011

Citing 8
Cited 0

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Cooperative Multi-Agent Learning: The State of the Art

Autonomous Agents and Multi-Agent Systems
Hybridizing evolutionary computation and reinforcement learning for the design of almost universal controllers for autonomous robots

Neurocomputing
On the potential contributions of hybrid intelligent approaches to Multicomponent Robotic System development

Information Sciences: an International Journal
Linked multi-component mobile robots: Modeling, simulation and control

Robotics and Autonomous Systems
Towards concurrent Q-learning on linked multi-component robotic systems

HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part II
Linked multicomponent robotic systems: basic assessment of linking element dynamical effect

HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part I
A Comprehensive Survey of Multiagent Reinforcement Learning

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

Quantified Score

Hi-index	0.00

Visualization

Abstract

Applying conventional Q-Learning to Multi-Component Robotic Systems (MCRS) increasing the number of components produces an exponential growth of state storage requirements. Modular approaches limit the state size growth to be polynomial on the number of components, allowing more manageable state representation and manipulation. In this article, we advance on previous works on a modular Q-learning approach to learn the distributed control of a Linked MCRS. We have chosen a paradigmatic application of this kind of systems using only local rewards: a set of robots carrying a hose from some initial configuration to a desired goal. The hose dynamics are simplified to be a distance constraint on the robots positions.