Recent AI Dissertations Decision Theory and the Cost of Planning Leo Hartman Dept. of C o m p u t e r Science University of Rochester Rochester N Y 14627 leo@cs.rochestor.edu The dissertation shows how it is possible for a planner to make decisions that are sensitive to the computational resources that it expends. The approach explored here ignores the distinction between planning and executing a plan and interprets planning procedures as actions with uncertain outcomes. This approach allows a planner to use standard decision theoretic techniques to select which among a set of alternative procedures is a better gamble. The hypotheses that underlie this work are that an autonomous agent must monitor its resource expenditure in order to be successful and that computation is an important and valuable resource. The main points of this thesis are: (1) it is possible for planners to make local inexpensive decisions that account for essentially their entire resource expenditure (2) there are limitations to what a planner is able to infer about optimal strategies (3) it is possible for planners to be sensitive to the statistical properties of their problem solving environments. (available as Technical Report 355, September 1990) Integrating Rules
End of preview. The entire article is 2 pages. To view the full-text, please rent this article to continue.
/lp/association-for-computing-machinery/recent-ai-dissertations-q18oVnYjIy
Welcome to DeepDyve! Rent Premier Research Articles and Save Up to 90%
Recent AI Dissertations
Johnson, Lewis
Follow ACM SIGART Bulletin
, Volume 2 (5)
Association for Computing Machinery – Sep 1, 1991
More Info
More Like This Article
View All dataSource[]=actageo&dataSource[]=aspet&dataSource[]=aaos&dataSource[]=aacc&dataSource[]=aacr&dataSource[]=aea&dataSource[]=aip&dataSource[]=ajnr&dataSource[]=ams&dataSource[]=aps_physical&dataSource[]=appi_book&dataSource[]=appi_journal&dataSource[]=apha&dataSource[]=asip&dataSource[]=asm&dataSource[]=asn&dataSource[]=aspb&dataSource[]=avs&dataSource[]=annual_reviews&dataSource[]=arxiv&dataSource[]=acm&dataSource[]=berghahn&dataSource[]=cabi&dataSource[]=clinical_trials&dataSource[]=dailymed&dataSource[]=degruyter&dataSource[]=du_press&dataSource[]=esa&dataSource[]=eu_press&dataSource[]=elsevier&dataSource[]=emerald&dataSource[]=ejtr&dataSource[]=emea&dataSource[]=epo&dataSource[]=faseb&dataSource[]=gsa&dataSource[]=health_affairs&dataSource[]=hindawi&dataSource[]=imanager&dataSource[]=imedpub&dataSource[]=informa_healthcare&dataSource[]=informs&dataSource[]=iop&dataSource[]=iucr&dataSource[]=iospress&dataSource[]=jbjs&dataSource[]=leftcoast&dataSource[]=lu_press&dataSource[]=mesharpe&dataSource[]=mary_ann_liebert&dataSource[]=medline&dataSource[]=mit_press&dataSource[]=nature&dataSource[]=oxford&dataSource[]=pier_professional&dataSource[]=pnas&dataSource[]=portlandpress&dataSource[]=psyc_articles&dataSource[]=psyc_books&dataSource[]=psyc_critiques&dataSource[]=plos_journal&dataSource[]=pubmed_central&dataSource[]=rsna&dataSource[]=rockefeller&dataSource[]=rcn&dataSource[]=ria&dataSource[]=rsc&dataSource[]=sage&dataSource[]=spie&dataSource[]=springer_journal&dataSource[]=springer&dataSource[]=taylor_francis&dataSource[]=aps&dataSource[]=the_scientist&dataSource[]=uc_press&dataSource[]=uspto_abstract&dataSource[]=wiley&dataSource[]=pct
© 2012 DeepDyve, Inc. All rights reserved.
Terms of Service | Privacy Policy
