| Title: |
COMPOSER: A Probabilistic Solution to the Utility Problem in Speed-up Learning. |
| Language: |
English |
| Authors: |
Gratch, Jonathan; DeJong, Gerald; Illinois Univ., Urbana. Dept. of Computer Science. |
| Peer Reviewed: |
N |
| Page Count: |
17 |
| Publication Date: |
1992 |
| Sponsoring Agency: |
National Science Foundation, Washington, DC. |
| Document Type: |
Information Analyses; Reports - Research |
| Descriptors: |
Algorithms; Artificial Intelligence; Comparative Analysis; Computer System Design; Learning Strategies; Planning; Probability; Problem Solving; Research Needs; Search Strategies; Statistical Analysis; Systems Development |
| Abstract: |
In machine learning there is considerable interest in techniques which improve planning ability. Initial investigations have identified a wide variety of techniques to address this issue. Progress has been hampered by the utility problem, a basic tradeoff between the benefit of learned knowledge and the cost to locate and apply relevant knowledge. In this paper we describe the COMPOSER system. COMPOSER embodies a probabilistic solution to the utility problem. It is implemented in the PRODIGY architecture. We compare COMPOSER to four other approaches which appear in the literature: (1) PRODIGY/EBL's Utility Analysis; (2) STATIC's Nonrecursive Hypothesis; (3) DYNAMIC: A Composite System; and (4) PALO's Chernoff Bounds. (Contains 24 references.) (Author/ALF) |
| Entry Date: |
1993 |
| Accession Number: |
ED353955 |
| Database: |
ERIC |