by S Buck, F Stulp, M Beetz and T 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:
Machine Control Using Radial Basis Value Functions and Inverse State Projection (S Buck, F Stulp, M Beetz and T Schmitt), In Proc. of the IEEE Intl. Conf. on Automation, Robotics, Control, and Vision, 2002.
Bibtex Entry:
@inproceedings{buck_machine_2002,
author = {S Buck and F Stulp and M Beetz and T 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},
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.},
}