Decomposition Techniques for Planning in Stochastic Domains

IJCAI International Joint Conference on Artificial Intelligence

Volumn 2, Issue , 1995, Pages 1121-1127

  Dean, Thomas ^a   Lin, Shieu Hong ^a  

^a BROWN UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ARTIFICIAL INTELLIGENCE; BEHAVIORAL RESEARCH; LEARNING ALGORITHMS; STOCHASTIC SYSTEMS; UNCERTAINTY ANALYSIS;

COMPUTING POLICIES; DECOMPOSITION TECHNIQUE; DISCRETE TIME; LOCAL PROBLEMS; MARKOV DECISION PROCESSES; PLANNING PROBLEM; STATE-SPACE; STOCHASTIC AUTOMATA; STOCHASTIC DOMAINS; UNCERTAINTY;

MARKOV PROCESSES;

EID: 85168151397     PISSN: 10450823     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (26)

1. [Bellman 196l] Richard Bellman Adaptivt ( ontrol Processes Princeton University Press Princeton New Jersey, 1961
2. [Boutiher et al , 1995] Craig Boutiher Richard Dearden and Moises Goldszmidt Exploiting structure in policy construction In Procecdings of the 1995 Inter national Joint Conference on Artificial Intelligence, 1995
3. [( aines and Wang 1990] Peter E ( aines and S Wang (OCOLOG A conditional observer and controller logic for finite machines In Proceedings of tht 29th IEEE Conference on Decision and Control Hawaii 1990
4. [( hvatal, 1980] Vasek Chvalal / irn-ar Programmmq W H Freeman and ( oinpany, 1980
5. [Danlzig and Wolfe, 1960] George Dantzig and Philip Wolfe Decomposition principle for dynamic programs Operations Research 8(l) 101 111,1900
6. [E)ean and Kanazawa, 1989] Thomas Dean and Keiji Kanazawa A model for reasoning about persistnce and causation Computational Intelliquence, 5(3) 112- 150 1989
7. [Dean and Lin 1995] Thomas Dean and Shieu-Hong 1 in Decomposition techniques for planning in stochastic domains Technical Report ( S-95-08, Brown University Department of Computer Science 1995
8. [Dean et al , 1993] Thomas Dean, Leslie Kaelbling, lak Rinnan, and Ann Nicholson Planning with deadlines in stochastic domains In Proceedings AAAI 93 pages 574 579 AAAI 1993
9. [Dean et al , 1995] Thomas Dean, Leslie Kaelbhng, Jak Kirman aud Ann Nicholson Planning under time constraints in stochastic domains To appear in Artificial Intelligence, 1995
10. [D'Epenoux, 1963] F D'Epenoux Sur un probleme de production et de stockage dans 1 aleatoire Management Science, 10 98-108, 1963
11. [Derman, 1970] Cyrus Derinan Finite State Markovtan Decision Processes Cambridge University Press New York, 1970
12. [Fikes and Nilsson 1971] Richard Fikes and Nils J Nilsson Strip* A new approach to the application of theorem proving to problem solving Artificial Intdligenct, 2 189-208, 1971
13. [Howard I960] Ronald A Howard Dynamic Program mmg and Markov Processes MI T Press, Cambridge, Massachusetts 1960
14. [Kaelbhng, 1993] Leslie Park Kaelbhng Hierarchical learning in stochastic domains A preliminary report In Proceedings Tenth International C onftrtnce on Ma chme Learning, 1993
15. [Knoblock, 199l] Craig A Knoblork Search reduction in hierarchical problem solving In Proceedings 4 4 4/- 91 pages 686 691 AAAI, 1991
16. [Korf, 1985] Richard Korf Macro-operators \ weak method for learning Artificial InUlligtnet 26 35 77 1985
17. [Kushnei and Chen 1974] Harold J Kushncr and C hing-Hui Chen Decomposition of systems governed by Markov chains IEEE Transactions on Automatic (ontrol AC-19(5) 501-507,1974
18. [Kushner and Kleinman, 1971] H 1 Kushner and A ) Kleinman Mathematical programming and the ton trul of Markov chains International Journal on Con trot 13(5) 801-820, 1971
19. [Lasdon, 1970] Leon S las-don Optimization Theory for I argt Systems. Macrinllan ( ornpany 1970
20. (/in and Dean 1991] Shreu u-Hong inand I nomas Dean Exploiting locality in temporal reasoning In E Sandewall and C Backstrom edilors (inrent Trends in 1/ Planning, Amsterdam, 1994 10S Press
21. [Moore and Alkeson, 1995] Andrew W Moore and ( linstoplier G Atkeson The parti-game algorithm for variable resolution reinforcement learning in multich mensional state spares To appear in Machine Learning 1995
22. [MS Be-araa, 1990] H D Sherah MS Bazaraa J I larvis Linear Programming and Ntwork Flours john Wilev & Sons New "York 1990
23. [Papadnnitriou and Tsitsikhs 1987] C hnstos H Papadimitnou and John N Isltsiklis The complexily of Markov chain decision processes Mathematu of Opt rations Research 12(3)441-40 1987
24. [Puterman, 1994] Martin L Pu term an Maihoi l)ta - sion Processes John Wiley &. Sons, New York 1994
25. [Sacerdoh, 1974] Earl Sacerdoti Planning in a hierarchy of abstraction spaces Artificial Intethqence 7 231- 272 1974
26. [Zhong and Wonharn, 1990] H Zhong and W M Wonham On the consistency of hierarchical supervision in discrele-event systems IEEE Transactions on 4u tomatic Control, 35(10) 1125-11 14, 1990