On the Job Training
| dc.creator | Holt, Jason E. | |
| dc.date | 2005-06-22 | |
| dc.date.accessioned | 2026-07-07T03:23:10Z | |
| dc.date.available | 2026-07-07T03:23:10Z | |
| dc.description | We 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.description | 8 pages, submitted to NIPS 2005 | |
| dc.identifier | https://arxiv.org/abs/cs/0506085 | |
| dc.identifier | http://arxiv.org/abs/cs/0506085 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/32838 | |
| dc.subject | Machine Learning | |
| dc.subject | K.3.2 | |
| dc.title | On the Job Training | |
| dc.type | text |