Point-based backup for decentralized POMDPs: Complexity and new algorithms

Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS

Volumn 3, Issue , 2010, Pages 1315-1322

  Kumar, Akshat ^a   Zilberstein, Shlomo ^a  

^a Biologically Inspired Neural and Dynamical Systems Laboratory   (United States)

Author keywords

DEC POMDPs; Multiagent planning

Indexed keywords

APPROXIMATION ALGORITHMS; AUTONOMOUS AGENTS; COMPUTATIONAL COMPLEXITY; DECISION MAKING; OPTIMIZATION;

APPROXIMATION SCHEME; DEC-POMDP; DECENTRALISED; HIGH COMPLEXITY; MULTI-AGENT DECISION MAKING; MULTI-AGENT PLANNING; OPTIMAL ALGORITHM; POINT-BASED; POINT-BASED METHODS; SCALING-UP;

MULTI AGENT SYSTEMS;

EID: 84899456155     PISSN: 15488403     EISSN: 15582914     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (19)

1. C. Amato, J. Dibangoye, and S. Zilberstein. Incremental policy generation for finite-horizon DEC-POMDPs. In Proc. of the Nineteenth International Conf. on Automated Planning and Scheduling, pages 2-9, 2009.
2. R. Becker, S. Zilberstein, V. Lesser, and C. V. Goldman. Solving transition independent decentralized markov decision processes. Journal of Artificial Intelligence Research, 22:423-455, 2004.
3. D. S. Bernstein, R. Givan, N. Immerman, and S. Zilberstein. The complexity of decentralized control of Markov decision processes. Mathematics of Operations Research, 27:819-840, 2002.
4. A. Carlin and S. Zilberstein. Value-based observation compression for DEC-POMDPs. In Proc. of the Seventh International Joint Conf. on Autonomous Agents and Multiagent Systems, pages 501-508, 2008.
5. R. Cogill and S. Lall. An approximation algorithm for the discrete team decision problem. SIAM Journal on Control and Optimization, 45(4):1359-1368, 2006.
6. S. de Givry, F. Heras, M. Zytnicki, and J. Larrosa. Existential arc consistency: Getting closer to full arc consistency in weighted CSPs. In Proc. of the International Joint Conf. on Artificial Intelligence, pages 84-89, 2005.
7. R. Dechter. Bucket elimination: A unifying framework for reasoning. Artificial Intelligence, 113(1-2):41-85, 1999.
8. J. S. Dibangoye, A.-I. Mouaddib, and B. Chaib-draa. Point-based incremental pruning heuristic for solving finite-horizon DEC-POMDPs. In Proc. of the Eighth International Joint Conf. on Autonomous Agents and Multiagent Systems, pages 569-576, 2009.
9. A. Kumar, S. Zilberstein. Constraint-based dynamic programming for decentralized POMDPs with structured interactions. In Proc. of the Eighth International Joint Conf. on Autonomous Agents and Multiagent Systems, pages 561-568, 2009.
10. R. Emery-Montemerlo, G. Gordon, J. Schneider, and S. Thrun. Approximate solutions for partially observable stochastic games with common payoffs. In Proc. of the Third International Joint Conf. on Autonomous Agents and Multiagent Systems, pages 136-143, 2004.
11. R. Marinescu and R. Dechter. AND/OR branch-and-bound search for graphical models. In Proc. of the International Joint Conf. on Artificial Intelligence, pages 224-229, 2005.
12. R. Nair, M. Tambe, M. Yokoo, D. Pynadath, and S. Marsella. Taming decentralized POMDPs: Towards efficient policy computation for multiagent settings. In Proc. of the International JointConf. on Artificial Intelligence, pages 705-711, 2003.
13. R. Nair, P. Varakantham, M. Tambe, and M. Yokoo. Networked distributed POMDPs: A synthesis of distributed constraint optimization and POMDPs. In Proc. of the Twentieth National Conf. on Artificial Intelligence, pages 133-139, 2005.
14. F. A. Oliehoek, M. T. J. Spaan, and N. A. Vlassis. Optimal and approximate q-value functions for decentralized POMDPs. Journal of Artificial Intelligence Research, 32:289-353, 2008.
15. J. Pineau, G. Gordon, and S. Thrun. Anytime point-based approximations for large POMDPs. Journal of Artificial Intelligence Research, 27:335-380, 2006.
16. S. Seuken and S. Zilberstein. Improved memory-bounded dynamic programming for decentralized POMDPs. In Proc. of the Twenty-Third Conf. on Uncertainty in Artificial Intelligence, 2007.
17. S. Seuken and S. Zilberstein. Memory-bounded dynamic programming for DEC-POMDPs. In Proc. of the Twentieth International Joint Conf. on Artificial Intelligences, pages 2009-2015, 2007.
18. M. Spaan and N. Vlassis. Perseus: Randomized point-based value iteration for POMDPs. Journal of Artificial Intelligence Research, 24:195-220, 2005.
19. J. N. Tsitsiklis and M. Äthans. On the complexity of decentralized decision making and detection problems. IEEE Trans. on Automatic Control, 30(2):440-446, 1985.