Accession Number : ADA554949


Title :   Case-Based Reasoning in Transfer Learning


Descriptive Note : Conference paper


Corporate Author : KNEXUS RESEARCH CORP SPRINGFIELD VA


Personal Author(s) : Aha, David W ; Molineaux, Matthew ; Sukthankar, Gita


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a554949.pdf


Report Date : Jan 2009


Pagination or Media Count : 16


Abstract : 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.


Descriptors :   *ARTIFICIAL INTELLIGENCE , *COMPUTER GAMES , *LEARNING MACHINES , *MULTIAGENT SYSTEMS , *REASONING , *TEAMS(PERSONNEL) , ALGORITHMS , CLUSTERING , SYMPOSIA


Subject Categories : Computer Programming and Software
      Cybernetics


Distribution Statement : APPROVED FOR PUBLIC RELEASE