Conservative and Reward-driven Behavior Selection in a Commonsense Reasoning Framework

AAAI Press
Publication Type:
Conference Proceeding
2009 AAAI Symposium: Multirepresentational Architectures for Human-Level Intelligence, 2009, pp. 14 - 19
Issue Date:
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2009003344OK.pdf840.61 kB
Adobe PDF
Comirit is a framework for commonsense reasoning that combines simulation, logical deduction and passive machine learning. While a passive, observation-driven approach to learning is safe and highly conservative, it is limited to interaction only with those objects that it has previously observed. In this paper we describe a preliminary exploration of methods for extending Comirit to allow safe action selection in uncertain situations, and to allow reward-maximizing selection of behaviors.
Please use this identifier to cite or link to this item: