Grounding Abstraction is Predictive Representations
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. .
Abstract
This paper proposes a systematic approach of representing abstract features in terms of low-level, subjective state representations. We demonstrate that a mapping between the agent's predictive state representation and an abstract feature representation can be derived automatically from high-level training data supplied by the designer. Our empirical evaluation demonstrates that an experience-oriented state representation built around a single-bit sensor can represent useful abstract features such as "back against a wall," "in a corner," or "in a room". As a result, the agent gains virtual sensors that could be used by its control policy.
@inproceedings{ijcai2007p174,
title = {Grounding Abstraction is Predictive Representations},
author = {Tanner, Brian and Bulitko, Vadim and Koop, Anna and Paduraru, Cosmin},
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},
year = {2007},
url = {https://ijcai.org/proceedings/2007/174},
}
TY - CPAPER TI - Grounding Abstraction is Predictive Representations AU - Tanner, Brian AU - Bulitko, Vadim AU - Koop, Anna AU - Paduraru, Cosmin T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 UR - https://ijcai.org/proceedings/2007/174 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
