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. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1007/978-3-642-02998-1_4 | ICCBR |
Keywords | Field | DocType |
american football,baseline approach,source task,control task,transfer learning,target task,case-based reasoning,alternative approach,positive transfer learning,case-based reinforcement learner,tl method,artificial intelligence,reasoning,clustering,multiagent systems,algorithms,case base reasoning | Football,Multi-task learning,Computer science,Transfer of learning,Multi-agent system,Exploit,Unsupervised learning,Artificial intelligence,Case-based reasoning,Cluster analysis,Machine learning | Conference |
Volume | ISSN | Citations |
5650 | 0302-9743 | 6 |
PageRank | References | Authors |
0.52 | 23 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
David W. Aha | 1 | 4103 | 620.93 |
Matthew Molineaux | 2 | 116 | 13.83 |
Gita Sukthankar | 3 | 538 | 60.40 |