Strategy Learning for Reasoning Agents
Abstract
We present a method for knowledge-based agents to learn strategies. Using techniques of inductive logic programming, strategies are learned in two steps: A given example set is first generalized into an overly general theory, which then gets refined. We show how a learning agent can exploit background knowledge of its actions and environment in order to restrict the hypothesis space, which enables the learning of complex logic program clauses. This is a first step toward the long term goal of adaptive, reasoning agents capable of changing their behavior when appropriate.
Cite
Text
Skubch and Thielscher. "Strategy Learning for Reasoning Agents." European Conference on Machine Learning, 2005. doi:10.1007/11564096_75Markdown
[Skubch and Thielscher. "Strategy Learning for Reasoning Agents." European Conference on Machine Learning, 2005.](https://mlanthology.org/ecmlpkdd/2005/skubch2005ecml-strategy/) doi:10.1007/11564096_75BibTeX
@inproceedings{skubch2005ecml-strategy,
title = {{Strategy Learning for Reasoning Agents}},
author = {Skubch, Hendrik and Thielscher, Michael},
booktitle = {European Conference on Machine Learning},
year = {2005},
pages = {733-740},
doi = {10.1007/11564096_75},
url = {https://mlanthology.org/ecmlpkdd/2005/skubch2005ecml-strategy/}
}