IMPROVED REVISION OF RANKING FUNCTIONS FOR THE GENERALIZATION OF BELIEF IN THE CONTEXT OF UNOBSERVED VARIABLES

Klaus Häming, Gabriele Peters

2011

Abstract

To enable a reinforcement learning agent to acquire symbolical knowledge, we augment it with a high-level knowledge representation. This representation consists of ordinal conditional functions (OCF) which allow it to rank world models. By this means the agent is enabled to complement the self-organizing capabilities of the low-level reinforcement learning sub-system by reasoning capabilities of a high-level learning component. We briefly summarize the state-of-the-art method how new information is included into the OCF. To improve the emergence of plausible behavior, we then introduce a modification of this method. The viability of this modification is examined first, for the inclusion of conditional information with negated consequents and second, for the generalization of belief in the context of unobserved variables. Besides providing a theoretical justification for this modification, we also show the advantages of our approach in comparison to the state-of-the-art method of revision in a reinforcement learning application.

Paper Citation

in Harvard Style

Häming K. and Peters G. (2011). IMPROVED REVISION OF RANKING FUNCTIONS FOR THE GENERALIZATION OF BELIEF IN THE CONTEXT OF UNOBSERVED VARIABLES . In Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011) ISBN 978-989-8425-84-3, pages 118-123. DOI: 10.5220/0003669501180123

in Bibtex Style

@conference{ncta11,
author={Klaus Häming and Gabriele Peters},
title={IMPROVED REVISION OF RANKING FUNCTIONS FOR THE GENERALIZATION OF BELIEF IN THE CONTEXT OF UNOBSERVED VARIABLES},
booktitle={Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011)},
year={2011},
pages={118-123},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003669501180123},
isbn={978-989-8425-84-3},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011)
TI - IMPROVED REVISION OF RANKING FUNCTIONS FOR THE GENERALIZATION OF BELIEF IN THE CONTEXT OF UNOBSERVED VARIABLES
SN - 978-989-8425-84-3
AU - Häming K.
AU - Peters G.
PY - 2011
SP - 118
EP - 123
DO - 10.5220/0003669501180123