Persönlicher Status und Werkzeuge

Home Publications
Approximating the Value Function for Continuous Space Reinforcement Learning in Robot Control (bibtex)
@INPROCEEDINGS{buck_approximating_2002,
  author = {Buck, Sebastian and Beetz, Michael and Schmitt, Thorsten},
  title = {Approximating the Value Function for Continuous Space Reinforcement
	Learning in Robot Control},
  booktitle = {Proc. of the {IEEE} Intl. Conf. on Intelligent Robots and Systems},
  year = {2002},
  abstract = {Many robot learning tasks are very difficult to solve: their state
	spaces are high dimensional, variables and command parameters are
	continuously valued, and system states are only partly observable.
	In this paper, we propose to learn a continuous space value function
	for reinforcement learning using neural networks trained from data
	of exploration runs. The learned function is guaranteed to be a lower
	bound for, and reproduces the characteristic shape of, the accurate
	value function. We apply our approach to two robot navigation tasks,
	discuss how to deal with possible problems occurring in practice,
	and assess its performance.}
}
Powered by bibtexbrowser
Export as PDF or BIB
Back to Publications
Last edited 29.01.2013 17:37 by Quirin Lohr