Abstract
This thesis develops methods of task localization, task similarity discovery, and task transfer for eventual use in a reinforcement learning task library system, which can effectively “learn to learn,” improving its performance as it encounters various tasks over the lifetime of the learning system.
Degree
MS
College and Department
Physical and Mathematical Sciences; Computer Science
Rights
http://lib.byu.edu/about/copyright/
BYU ScholarsArchive Citation
Carroll, James Lamond, "Task Localization, Similarity, and Transfer; Towards a Reinforcement Learning Task Library System" (2005). Theses and Dissertations. 579.
https://scholarsarchive.byu.edu/etd/579
Date Submitted
2005-07-07
Document Type
Thesis
Handle
http://hdl.lib.byu.edu/1877/etd901
Keywords
Reinforcement Learning, Learning to Learn, Lifelong Learning, Task Transfer, Task Libraries
Language
English