Representations for Action Selection Learning from Real-Time Observation of Task Experts
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.
@inproceedings{ijcai2007p102,
title = {Representations for Action Selection Learning from Real-Time Observation of Task Experts},
author = {Wood, Mark A. and Bryson, Joanna},
booktitle = {Proceedings of the Twentieth International Joint Conference on
Artificial Intelligence, {IJCAI-07}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ramon López de Mántaras},
pages = {641--645},
year = {2007},
url = {https://ijcai.org/proceedings/2007/102},
}
TY - CPAPER TI - Representations for Action Selection Learning from Real-Time Observation of Task Experts AU - Wood, Mark A. AU - Bryson, Joanna T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 SP - 641 EP - 645 UR - https://ijcai.org/proceedings/2007/102 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
