---
title: "Representations for Action Selection Learning from Real-Time Observation of Task Experts"
authors:
  - "Mark A. Wood"
  - "Joanna Bryson"
doi: ""
url: "https://ijcai.org/proceedings/2007/102"
pdf: "https://ijcai.org/proceedings/2007/0102.pdf"
venue: "Proceedings of the Twentieth International Joint Conference on Artificial Intelligence"
year: 2007
pages: "641-645"
track: ""
keywords:
---

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

Mark A. Wood, Joanna Bryson

*Proceedings of the Twentieth International Joint Conference on Artificial Intelligence*, pages 641-645.

## 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.