Learning and Transferring Action Schemas
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 720-724.
Abstract
Jean is a model of early cognitive development based loosely on Piaget's theory of sensori-motor and pre-operational thought. Like an infant, Jean repeatedly executes schemas, gradually transferring them to new situations and extending them as necessary to accommodate new experiences. We model this process of accommodation with the Experimental State Splitting (ESS) algorithm. ESS learns elementary action schemas, which comprise controllers and maps of the expected dynamics of executing controllers in different conditions. ESS also learns compositions of action schemas called gists. We present tests of the ESS algorithm in three transfer learning experiments, in which Jean transfers learned gists to new situations in a real time strategy military simulator.
@inproceedings{ijcai2007p115,
title = {Learning and Transferring Action Schemas},
author = {Cohen, Paul R. and Chang, Yu-Han and Morrison, Clayton T. and Beal, Carole R.},
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 = {720--724},
year = {2007},
url = {https://ijcai.org/proceedings/2007/115},
}
TY - CPAPER TI - Learning and Transferring Action Schemas AU - Cohen, Paul R. AU - Chang, Yu-Han AU - Morrison, Clayton T. AU - Beal, Carole R. T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 SP - 720 EP - 724 UR - https://ijcai.org/proceedings/2007/115 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
