Task Localization, Similarity, and Transfer; Towards a Reinforcement Learning Task Library System

<p>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.</p>

Name thesis:degree_name

MS

Grantor dc:publisher

Brigham Young University - Provo

Author dc:creator

• Carroll, James Lamond

• Reinforcement Learning
• Learning to Learn
• Lifelong Learning
• Task Transfer
• Task Libraries
• Computer Sciences

Language dc:language

English

Repository record dc:identifier

https://scholarsarchive.byu.edu/etd/579

OAI identifier oai:identifier

oai:scholarsarchive.byu.edu:etd-1578