Using policy gradient reinforcement learning on autonomous robot controllers

Loading...
Thumbnail Image
Penn collection
Departmental Papers (MEAM)
General Robotics, Automation, Sensing and Perception Laboratory
Degree type
Discipline
Subject
GRASP
robotics
controllers
programming
Policy Gradient Reinforcement Learning (PGRL)
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Contributor
Abstract

Robot programmers can often quickly program a robot to approximately execute a task under specific environment conditions. However, achieving robust performance under more general conditions is significantly more difficult. We propose a framework that starts with an existing control system and uses reinforcement feedback from the environment to autonomously improve the controller’s performance. We use the Policy Gradient Reinforcement Learning (PGRL) framework, which estimates a gradient (in controller space) of improved reward, allowing the controller parameters to be incrementally updated to autonomously achieve locally optimal performance. Our approach is experimentally verified on a Cye robot executing a room entry and observation task, showing significant reduction in task execution time and robustness with respect to un-modelled changes in the environment.

Advisor
Date of presentation
2003-10-27
Conference name
Departmental Papers (MEAM)
Conference dates
2023-05-16T21:37:49.000
Conference location
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
Copyright © 2003 IEEE. Reprinted from Proceedings of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003), volume 1, pages 406-411. Publisher URL: http://ieeexplore.ieee.org/xpl/tocresult.jsp?isNumber=27983&page=4 This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Pennsylvania's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.
Recommended citation
Collection