Representations for Learning Action Selection from Real-Time Observation of Task Experts

Mark A Wood, Joanna J Bryson

Research output: Contribution to conferencePaper

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.
Original languageEnglish
Pages641-646
Number of pages6
Publication statusPublished - 2007
Event20th International Joint Conference on Artificial Intelligence - Hyderabad, India
Duration: 6 Jan 200712 Jan 2007

Conference

Conference20th International Joint Conference on Artificial Intelligence
CountryIndia
CityHyderabad
Period6/01/0712/01/07

Cite this