TitleCase-based reasoning for transfer learning
Publication TypeConference Paper
Year of Publication2009
AuthorsAha, DW, Molineaux, M, Sukthankar, G
Conference NameInternational Conference on Case-Based Reasoning
Conference LocationSeattle, WA
Keywordscase-based reasoning, game AI, machine learning, reinforcement learning, Transfer learning

Positive transfer learning (TL) occurs when, after gaining experience from learning how to solve a (source) task, the same learner can exploit this experience to improve performance and/or learning on a different (target) task. TL methods are typically complex, and case-based reasoning can support them in multiple ways. We introduce a method for recognizing intent in a source task, and then applying that knowledge to improve the performance of a case-based reinforcement learner in a target task. We report on its ability to significantly outperform baseline approaches for a control task in a simulated game of American football. We also compare our approach to an alternative approach where source and target task learning occur concurrently, and discuss the tradeoffs between them.

Refereed DesignationRefereed
Full Text
NRL Publication Release Number: 
machine learning
transfer learning
case-based reasoning
reinforcement learning
game AI