---
title: "Grounding Abstraction is Predictive Representations"
authors:
  - "Brian Tanner"
  - "Vadim Bulitko"
  - "Anna Koop"
  - "Cosmin Paduraru"
doi: ""
url: "https://ijcai.org/proceedings/2007/174"
pdf: "https://ijcai.org/proceedings/2007/0174.pdf"
venue: "Proceedings of the Twentieth International Joint Conference on Artificial Intelligence"
year: 2007
pages: ""
track: ""
keywords:
---

# Grounding Abstraction is Predictive Representations

Brian Tanner, Vadim Bulitko, Anna Koop, Cosmin Paduraru

*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.