{"type":"ScholarlyArticle","title":"Grounding Abstraction is Predictive Representations","authors":[{"name":"Brian Tanner","slug":"brian-tanner","given":"Brian","family":"Tanner","affiliation":""},{"name":"Vadim Bulitko","slug":"vadim-bulitko","given":"Vadim","family":"Bulitko","affiliation":""},{"name":"Anna Koop","slug":"anna-koop","given":"Anna","family":"Koop","affiliation":""},{"name":"Cosmin Paduraru","slug":"cosmin-paduraru","given":"Cosmin","family":"Paduraru","affiliation":""}],"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.","doi":null,"url":"https://ijcai.org/proceedings/2007/174","pdf":"https://ijcai.org/proceedings/2007/0174.pdf","markdown":"https://ijcai.org/proceedings/2007/174.md","bibtex":"https://ijcai.org/proceedings/2007/bibtex/174","volume":{"slug":"2007","title":"Proceedings of the Twentieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2007","url":"https://ijcai.org/proceedings/2007/","year":2007,"location":"Hyderabad, India","dates":"","editors":"Ramon López de Mántaras","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":174,"pages":{"first":null,"last":null},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}