Optimally solving Dec-POMDPs as continuous-state MDPs

IJCAI International Joint Conference on Artificial Intelligence

Volumn , Issue , 2013, Pages 90-96

  Dibangoye, Jilles Steeve ^a   Amato, Christopher ^b   Buffet, Olivier ^a   Charpillet, François ^a  

^a UNIVERSITÉ DE LORRAINE   (France)

^b MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMBINATORIAL PROBLEM; COMPUTING POLICIES; DIMENSION REDUCTION; EXPONENTIAL GROWTH; LOW-DIMENSIONAL MANIFOLDS; LOW-DIMENSIONAL REPRESENTATION; PARTIALLY OBSERVABLE MARKOV DECISION PROCESS; REAL-WORLD PROBLEM;

ARTIFICIAL INTELLIGENCE;

ALGORITHMS;

EID: 84896064243     PISSN: 10450823     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (26)

1. Christopher Amato, Jilles S. Dibangoye, and Shlomo Zilberstein. Incremental policy generation for finite-horizon DEC-POMDPs. In ICAPS, 2009.
2. Raghav Aras and Alain Dutech. An investigation into mathematical programming for finite horizon decentralized POMDPs. JAIR, 37:329-396, 2010.
3. J. Andrew Bagnell, Sham Kakade, Andrew Ng, and Jeff Schneider. Policy search by dynamic programming. In NIPS, volume 16, 2003.
4. Daniel S. Bernstein, Robert Givan, Neil Immerman, and Shlomo Zilberstein. The complexity of decentralized control of Markov decision processes. Mathematics of Operations Research, 27(4), 2002.
5. Daniel S. Bernstein, Christopher Amato, Eric A. Hansen, and Shlomo Zilberstein. Policy iteration for decentralized control of Markov decision processes. JAIR, 34:89-132, 2009.
6. Abdeslam Boularias and Brahim Chaib-draa. Exact dynamic programming for decentralized POMDPs with lossless policy compression. In ICAPS, pages 20-27, 2008.
7. Arnaud Canu and Abdel-Illah Mouaddib. Collective decision under partial observability - a dynamic local interaction model. In IJCCI (ECTAFCTA), pages 146-155, 2011.
8. D. P. De Farias and B. Van Roy. The linear programming approach to approximate dynamic programming. Operations Research, 51(6):850-865, 2003.
9. Jilles S. Dibangoye, Abdel-Illah Mouaddib, and Brahim Chaib-draa. Toward error-bounded algorithms for infinite-horizon DEC-POMDPs. In AAMAS, pages 947-954, 2011.
10. Jilles S. Dibangoye, Christopher Amato, and Arnaud Doniec. Scaling up decentralized MDPs through heuristic search. In UAI, pages 217-226, 2012.
11. Jilles S. Dibangoye, Christopher Amato, Arnaud Doniec, and François Charpillet. Producing efficient error-bounded solutions for transition independent decentralized MDPs. In AAMAS, 2013.
12. Eric A. Hansen, Daniel S. Bernstein, and Shlomo Zilberstein. Dynamic programming for partially observable stochastic games. In AAAI, pages 709- 715, 2004.
13. Ronald A. Howard. Dynamic Programming and Markov Processes. The M.I.T. Press, 1960.
14. Akshat Kumar and Shlomo Zilberstein. Constraint-based dynamic programming for decentralized POMDPs with structured interactions. In AAMAS, pages 561-568, 2009.
15. Ranjit Nair, Pradeep Varakantham, Milind Tambe, and Makoto Yokoo. Networked distributed POMDPs: A synthesis of distributed constraint optimization and POMDPs. In AAAI, pages 133-139, 2005.
16. Frans A. Oliehoek, Matthijs T. J. Spaan, and Nikos A. Vlassis. Optimal and approximate Qvalue functions for decentralized POMDPs. JAIR, 32:289-353, 2008.
17. Frans A. Oliehoek, Shimon Whiteson, and Matthijs T. J. Spaan. Lossless clustering of histories in decentralized POMDPs. In AAMAS, pages 577- 584, 2009.
18. Frans A. Oliehoek, Matthijs T. J. Spaan, Christopher Amato, and Shimon Whiteson. Incremental clustering and expansion for faster optimal planning in Dec-POMDPs. JAIR, 46:449-509, 2013.
19. Frans A. Oliehoek. Sufficient plan-time statistics for decentralized POMDPs. In IJCAI, 2013.
20. Azaria Paz. Introduction to probabilistic automata (Computer science and applied mathematics). Academic Press, Inc., Orlando, FL, USA, 1971.
21. Warren B. Powell. Approximate Dynamic Programming: Solving the Curses of Dimensionality (Wiley Series in Probability and Statistics). Wiley- Interscience, 2007.
22. Guy Shani, Joelle Pineau, and Robert Kaplow. A survey of point-based POMDP solvers. JAAMAS, pages 1-51, 2012.
23. R. D. Smallwood and E. J. Sondik. The optimal control of partially observable Markov decision processes over a finite horizon. Operations Research, 21(5):1071-1088, 1973.
24. Trey Smith and Reid Simmons. Heuristic search value iteration for POMDPs. In UAI, pages 520-527, 2004.
25. Matthijs T. J. Spaan, Frans A. Oliehoek, and Christopher Amato. Scaling up optimal heuristic search in Dec-POMDPs via incremental expansion. In IJCAI, pages 2027-2032, 2011.
26. Daniel Szer, Francois Charpillet, and Shlomo Zilberstein. MAA*: A heuristic search algorithm for solving decentralized POMDPs. In UAI, pages 568- 576, 2005.