{"type":"ScholarlyArticle","title":"Representations for Action Selection Learning from Real-Time Observation of Task Experts","authors":[{"name":"Mark A. Wood","slug":"mark-a-wood","given":"Mark A.","family":"Wood","affiliation":""},{"name":"Joanna Bryson","slug":"joanna-bryson","given":"Joanna","family":"Bryson","affiliation":""}],"abstract":"The association of perception and action is key to learning by observation in general, and to program-level task imitation in particular. The question is how to structure this information such that learning is tractable for resource-bounded agents. By introducing a combination of symbolic representation with Bayesian reasoning, we demonstrate both theoretical and empirical improvements to a general-purpose imitation system originally based on a model of infant social learning. We also show how prior task knowledge and selective attention can be rigorously incorporated via loss matrices and Automatic Relevance Determination respectively.","doi":null,"url":"https://ijcai.org/proceedings/2007/102","pdf":"https://ijcai.org/proceedings/2007/0102.pdf","markdown":"https://ijcai.org/proceedings/2007/102.md","bibtex":"https://ijcai.org/proceedings/2007/bibtex/102","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":102,"pages":{"first":641,"last":645},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}