by Sebastian Buck, Freek Stulp, Michael Beetz and Thorsten Schmitt
Abstract:
Typical real world machine control tasks have some characteristics which makes them difficult to solve: Their state spaces are high-dimensional and continuous, and it may be impossible to reach a satisfying target state by exploration or human control. To overcome these problems, in this paper, we propose (1) to use radial basis functions for value function approximation in continuous space reinforcement learning and (2) the use of learned inverse projection functions for state space exploration. We apply our approach to path planning in dynamic environments and to an aircraft autolanding simulation, and evaluate its performance.
Reference:
Sebastian Buck, Freek Stulp, Michael Beetz and Thorsten Schmitt, "Machine Control Using Radial Basis Value Functions and Inverse State Projection", In Proc. of the IEEE Intl. Conf. on Automation, Robotics, Control, and Vision, 2002.
Bibtex Entry:
@inproceedings{Buc02Mac,
author = {Sebastian Buck and Freek Stulp and Michael Beetz and Thorsten Schmitt},
title = {{Machine Control Using Radial Basis Value Functions and Inverse State Projection}},
booktitle = {Proc. of the IEEE Intl. Conf. on Automation, Robotics, Control, and Vision},
year = {2002},
bib2html_pubtype = {Refereed Conference Paper},
bib2html_rescat = {Models, Learning, Action},
bib2html_groups = {AGILO},
bib2html_funding = {AGILO},
bib2html_keywords = {Robot},
abstract = {Typical real world machine control tasks have some characteristics
which makes them difficult to solve: Their state spaces are
high-dimensional and continuous, and it may be impossible to reach a
satisfying target state by exploration or human control. To overcome
these problems, in this paper, we propose (1) to use radial basis
functions for value function approximation in continuous space
reinforcement learning and (2) the use of learned inverse projection
functions for state space exploration. We apply our approach to path
planning in dynamic environments and to an aircraft autolanding
simulation, and evaluate its performance.}
}