Online Learning and Exploiting Relational Models in Reinforcement Learning

Croonenborghs, Tom; Ramon, Jan; Blockeel, Hendrik; Bruynooghe, Maurice

Online Learning and Exploiting Relational Models in Reinforcement Learning

Tom Croonenborghs, Jan Ramon, Hendrik Blockeel, Maurice Bruynooghe

Download BibTeX Cite

Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 726-730.

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.

Tom Croonenborghs, Jan Ramon, Hendrik Blockeel, and Maurice Bruynooghe. 2007. Online Learning and Exploiting Relational Models in Reinforcement Learning. In Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07. IJCAI, 726–730. https://ijcai.org/proceedings/2007/116

@inproceedings{ijcai2007p116,
  title     = {Online Learning and Exploiting Relational Models in Reinforcement Learning},
  author    = {Croonenborghs, Tom and Ramon, Jan and Blockeel, Hendrik and Bruynooghe, Maurice},
  booktitle = {Proceedings of the Twentieth International Joint Conference on
               Artificial Intelligence, {IJCAI-07}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  editor    = {Ramon López de Mántaras},
  pages     = {726--730},
  year      = {2007},
  url       = {https://ijcai.org/proceedings/2007/116},
}

TY  - CPAPER
TI  - Online Learning and Exploiting Relational Models in Reinforcement Learning
AU  - Croonenborghs, Tom
AU  - Ramon, Jan
AU  - Blockeel, Hendrik
AU  - Bruynooghe, Maurice
T2  - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2007
SP  - 726
EP  - 730
UR  - https://ijcai.org/proceedings/2007/116
ER  -