Online Learning and Exploiting Relational Models in Reinforcement Learning
Abstract
In recent years, there has been a growing interest in using rich representations such as relational languages for reinforcement learning. However, while expressive languages have many advantages in terms of generalization and reasoning, extending existing approaches to such a relational setting is a non-trivial problem. In this paper, we present a first step towards the online learning and exploitation of relational models. We propose a representation for the transition and reward function that can be learned online and present a method that exploits these models by augmenting Relational Reinforcement Learning algorithms with planning techniques. The benefits and robustness of our approach are evaluated experimentally.
Cite
Text
Croonenborghs et al. "Online Learning and Exploiting Relational Models in Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2007.Markdown
[Croonenborghs et al. "Online Learning and Exploiting Relational Models in Reinforcement Learning." International Joint Conference on Artificial Intelligence, 2007.](https://mlanthology.org/ijcai/2007/croonenborghs2007ijcai-online/)BibTeX
@inproceedings{croonenborghs2007ijcai-online,
title = {{Online Learning and Exploiting Relational Models in Reinforcement Learning}},
author = {Croonenborghs, Tom and Ramon, Jan and Blockeel, Hendrik and Bruynooghe, Maurice},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2007},
pages = {726-731},
url = {https://mlanthology.org/ijcai/2007/croonenborghs2007ijcai-online/}
}