A Teaching Method for Reinforcement Learning
Abstract
This paper presents a method for accelerating the learning rates of reinforcement learning algorithms. Reinforcement learning algorithms are known for their slow learning rates, and researchers have focused recently on increasing those rates. In this paper, a method that allows a human expert to interact in real-time with a reinforcement learning algorithm is shown to accelerate the learning process. Two experiments, each with a different domain and a different reinforcement learning algorithm, illustrate that the unobtrusive method accelerates learning by more than an order of magnitude
Cite
Text
Clouse and Utgoff. "A Teaching Method for Reinforcement Learning." International Conference on Machine Learning, 1992. doi:10.1016/B978-1-55860-247-2.50017-6Markdown
[Clouse and Utgoff. "A Teaching Method for Reinforcement Learning." International Conference on Machine Learning, 1992.](https://mlanthology.org/icml/1992/clouse1992icml-teaching/) doi:10.1016/B978-1-55860-247-2.50017-6BibTeX
@inproceedings{clouse1992icml-teaching,
title = {{A Teaching Method for Reinforcement Learning}},
author = {Clouse, Jeffery A. and Utgoff, Paul E.},
booktitle = {International Conference on Machine Learning},
year = {1992},
pages = {92-110},
doi = {10.1016/B978-1-55860-247-2.50017-6},
url = {https://mlanthology.org/icml/1992/clouse1992icml-teaching/}
}