Research

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


Reference:

Wood, M. A. and Bryson, J. J., 2007. Representations for Learning Action Selection from Real-Time Observation of Task Experts. In: 20th International Joint Conference on Artificial Intelligence, 2007-01-06 - 2007-01-12, Hyderabad.

Related documents:

This repository does not currently have the full-text of this item.
You may be able to access a copy if URLs are provided below.

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.

Details

Item Type Conference or Workshop Items (Paper)
CreatorsWood, M. A.and Bryson, J. J.
DepartmentsFaculty of Science > Computer Science
RefereedNo
StatusPublished
ID Code5266

Export

Actions (login required)

View Item