A walking robot learns to walk forward based on the feedback of an odometry sensor (wheel encoders). Reinforcement Learning / Dynamic Programming / Value Iteration. More information: http://www.tokic.com
@InProceedings{TEF09,
author = {Michel Tokic and Wolfgang Ertel and Joachim Fessler},
title = {The Crawler, A Class Room Demonstrator for Reinforcement Learning},
booktitle = {In Proceedings of the 22nd International Florida Artificial Intelligence Research Society Conference (FLAIRS 09)},
year = {2009},
address = {Menlo Park, California},
publisher = {AAAI Press}
}
For details see: http://www.tokic.com
He's got the heart of a champion!
uuuuuuuuu7 1 year ago
cool :D
TheYoGamer 1 year ago