{"type":"ScholarlyArticle","title":"Deictic Option Schemas","authors":[{"name":"Balaraman Ravindran","slug":"balaraman-ravindran","given":"Balaraman","family":"Ravindran","affiliation":""},{"name":"Andrew G. Barto","slug":"andrew-g-barto","given":"Andrew G.","family":"Barto","affiliation":""},{"name":"Vimal Mathew","slug":"vimal-mathew","given":"Vimal","family":"Mathew","affiliation":""}],"abstract":"Deictic representation is a representational paradigm, based on selective attention and pointers, that allows an agent to learn and reason about rich complex environments. In this article we present a hierarchical reinforcement learning framework that employs aspects of deictic representation. We also present a Bayesian algorithm for learning the correct representation for a given sub-problem and empirically validate it on a complex game environment.","doi":null,"url":"https://ijcai.org/proceedings/2007/165","pdf":"https://ijcai.org/proceedings/2007/0165.pdf","markdown":"https://ijcai.org/proceedings/2007/165.md","bibtex":"https://ijcai.org/proceedings/2007/bibtex/165","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":165,"pages":{"first":1023,"last":1027},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}