by M Beetz, A Kirsch and A Müller
Abstract:
In this paper, we extend the autonomous robot control and plan language RPL with constructs for specifying experiences, control tasks, learning systems and their parameterization, and exploration strategies. Using these constructs, the learning problems can be represented explicitly and transparently and become executable. With the extended language we rationally reconstruct parts of the AGILO autonomous robot soccer controllers and show the feasibility and advantages of our approach.
Reference:
RPL-LEARN: Extending an Autonomous Robot Control Language to Perform Experience-based Learning (M Beetz, A Kirsch and A Müller), In 3rd International Joint Conference on Autonomous Agents & Multi Agent Systems (AAMAS), 2004.
Bibtex Entry:
@inproceedings{beetz_rpl-learn:_2004,
author = {M Beetz and A Kirsch and A Müller},
title = {{RPL-LEARN:} Extending an Autonomous Robot Control Language to Perform
Experience-based Learning},
booktitle = {3rd International Joint Conference on Autonomous Agents \& Multi
Agent Systems ({AAMAS)}},
year = {2004},
abstract = {In this paper, we extend the autonomous robot control and plan language
{RPL} with constructs for specifying experiences, control tasks,
learning systems and their parameterization, and exploration strategies.
Using these constructs, the learning problems can be represented
explicitly and transparently and become executable. With the extended
language we rationally reconstruct parts of the {AGILO} autonomous
robot soccer controllers and show the feasibility and advantages
of our approach.},
}