On the Job Training

dc.creatorHolt, Jason E.
dc.date2005-06-22
dc.date.accessioned2026-07-07T03:23:10Z
dc.date.available2026-07-07T03:23:10Z
dc.descriptionWe propose a new framework for building and evaluating machine learning algorithms. We argue that many real-world problems require an agent which must quickly learn to respond to demands, yet can continue to perform and respond to new training throughout its useful life. We give a framework for how such agents can be built, describe several metrics for evaluating them, and show that subtle changes in system construction can significantly affect agent performance.
dc.description8 pages, submitted to NIPS 2005
dc.identifierhttps://arxiv.org/abs/cs/0506085
dc.identifierhttp://arxiv.org/abs/cs/0506085
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/32838
dc.subjectMachine Learning
dc.subjectK.3.2
dc.titleOn the Job Training
dc.typetext

Files

Collections