Grounding Abstractions in Predictive State Representations
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.
Cite
Text
Tanner et al. "Grounding Abstractions in Predictive State Representations." International Joint Conference on Artificial Intelligence, 2007.Markdown
[Tanner et al. "Grounding Abstractions in Predictive State Representations." International Joint Conference on Artificial Intelligence, 2007.](https://mlanthology.org/ijcai/2007/tanner2007ijcai-grounding/)BibTeX
@inproceedings{tanner2007ijcai-grounding,
title = {{Grounding Abstractions in Predictive State Representations}},
author = {Tanner, Brian and Bulitko, Vadim and Koop, Anna and Paduraru, Cosmin},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2007},
pages = {1077-1082},
url = {https://mlanthology.org/ijcai/2007/tanner2007ijcai-grounding/}
}