Effective Control Knowledge Transfer through Learning Skill and Representation Hierarchies
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 2054-2058.
Abstract
Learning capabilities of computer systems still lag far behind biological systems. One of the reasons can be seen in the inefficient re-use of control knowledge acquired over the lifetime of the artificial learning system. To address this deficiency, this paper presents a learning architecture which transfers control knowledge in the form of behavioral skills and corresponding representation concepts from one task to subsequent learning tasks. The presented system uses this knowledge to construct a more compact state space representation for learning while assuring bounded optimality of the learned task policy by utilizing a representation hierarchy. Experimental results show that the presented method can significantly outperform learning on a flat state space representation and the MAXQ method for hierarchical reinforcement learning.
@inproceedings{ijcai2007p331,
title = {Effective Control Knowledge Transfer through Learning Skill and Representation Hierarchies},
author = {Asadi, Mehran and Huber, Manfred},
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 = {2054--2058},
year = {2007},
url = {https://ijcai.org/proceedings/2007/331},
}
TY - CPAPER TI - Effective Control Knowledge Transfer through Learning Skill and Representation Hierarchies AU - Asadi, Mehran AU - Huber, Manfred T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 SP - 2054 EP - 2058 UR - https://ijcai.org/proceedings/2007/331 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
