Representations for Action Selection Learning from Real-Time Observation of Task Experts
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.
Cite
Text
Wood and Bryson. "Representations for Action Selection Learning from Real-Time Observation of Task Experts." International Joint Conference on Artificial Intelligence, 2007.Markdown
[Wood and Bryson. "Representations for Action Selection Learning from Real-Time Observation of Task Experts." International Joint Conference on Artificial Intelligence, 2007.](https://mlanthology.org/ijcai/2007/wood2007ijcai-representations/)BibTeX
@inproceedings{wood2007ijcai-representations,
title = {{Representations for Action Selection Learning from Real-Time Observation of Task Experts}},
author = {Wood, Mark A. and Bryson, Joanna},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2007},
pages = {641-646},
url = {https://mlanthology.org/ijcai/2007/wood2007ijcai-representations/}
}