Item


Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking

This paper proposes a field application of a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot in cable tracking task. The learning system is characterized by using a direct policy search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot ICTINEU AUV

© IEEE/RSJ International Conference on Intelligent Robots and Systems : 2008 : IROS 2008, 2008, p. 3635-3640

IEEE

Author: El-Fakdi Sencianes, Andrés
Carreras Pérez, Marc
Date: 2008
Abstract: This paper proposes a field application of a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot in cable tracking task. The learning system is characterized by using a direct policy search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot ICTINEU AUV
Format: application/pdf
Citation: El-Fakdi, A., i Carreras, M. (2008). IEEE/RSJ International Conference on Intelligent Robots and Systems : 2008 : IROS 2008, 3635 - 3640. Recuperat 06 maig 2010, a http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4650873
ISBN: 978-1-4244-2057-5
Document access: http://hdl.handle.net/10256/2178
Language: eng
Publisher: IEEE
Collection: Reproducció digital del document publicat a: http://dx.doi.org/10.1109/IROS.2008.4650873
Articles publicats (D-ATC)
Is part of: © IEEE/RSJ International Conference on Intelligent Robots and Systems : 2008 : IROS 2008, 2008, p. 3635-3640
Rights: Tots els drets reservats
Subject: Aprenentatge per reforç
Robots autònoms
Autonomous robots
Reinforcement learning
Title: Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking
Type: info:eu-repo/semantics/article
Repository: DUGiDocs

Subjects

Authors


Warning: Unknown: write failed: No space left on device (28) in Unknown on line 0

Warning: Unknown: Failed to write session data (files). Please verify that the current setting of session.save_path is correct (/var/lib/php5) in Unknown on line 0