Portable Option Discovery for Automated Learning Transfer in Object-Oriented Markov Decision Processes
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Special Track on Machine Learning. Pages 3856-3863.
Abstract
We introduce a novel framework for option discovery and learning transfer in complex domains that are represented as object-oriented Markov decision processes (OO-MDPs) [Diuk et al., 2008]. Our framework, Portable Option Discovery (POD), extends existing option discovery methods, and enables transfer across related but different domains by providing an unsupervised method for finding a mapping between object-oriented domains with different state spaces. The framework also includes heuristic approaches for increasing the efficiency of the mapping process. We present the results of applying POD to Pickett and Barto's [2002] PolicyBlocks and MacGlashan's [2013] Option-Based Policy Transfer in two application domains. We show that our approach can discover options effectively, transfer options among different domains, and improve learning performance with low computational overhead.
@inproceedings{ijcai2015p542,
title = {Portable Option Discovery for Automated Learning Transfer in Object-Oriented Markov Decision Processes},
author = {Topin, Nicholay and Haltmeyer, Nicholas and Squire, Shawn and Winder, John and desJardins, Marie and MacGlashan, James},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-15}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Qiang Yang and Michael Wooldridge},
pages = {3856--3863},
year = {2015},
month = {7},
note = {Special Track on Machine Learning},
url = {https://ijcai.org/proceedings/2015/542},
}
TY - CPAPER TI - Portable Option Discovery for Automated Learning Transfer in Object-Oriented Markov Decision Processes AU - Topin, Nicholay AU - Haltmeyer, Nicholas AU - Squire, Shawn AU - Winder, John AU - desJardins, Marie AU - MacGlashan, James T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 3856 EP - 3863 UR - https://ijcai.org/proceedings/2015/542 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: