Decentralized reinforcement learning applied to mobile robots

Conference paper (2017)

Authors

David L. Leottau Universidad de Santiago de Chile

Aashish Vatsyayan Student

Javier Ruiz-del-Solar Universidad de Santiago de Chile

R. Babuska Learning & Autonomous Control - Mechanical, Maritime and Materials Engineering

Research Group

Learning & Autonomous Control (Mechanical, Maritime and Materials Engineering) (TU Delft)

Reinforcement learning Decentralized control Multiagent learning Robot soccer

To reference this document use:

http://resolver.tudelft.nl/uuid:9b685faa-be71-44fd-b802-8eb8c1daee0d

More Info

expand_more

Published Date

2017

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical, Maritime and Materials Engineering

Department

Cognitive Robotics

Research Group

Learning & Autonomous Control

Abstract

In this paper, decentralized reinforcement learning is applied to a control problem with a multidimensional action space. We propose a decentralized reinforcement learning architecture for a mobile robot, where the individual components of the commanded velocity vector are learned in parallel by separate agents. We empirically demonstrate that the decentralized architecture outperforms its centralized counterpart in terms of the learning time, while using less computational resources. The method is validated on two problems: an extended version of the 3-dimensional mountain car, and a ball-pushing behavior performed with a differential-drive robot, which is also tested on a physical setup.

Files

Leottau2017_Chapter_Decentrali... (pdf)

(pdf | 0.928 Mb)

Download not available