Advertisement

Decentralized POMDPs

  • Frans A. Oliehoek
Chapter
Part of the Adaptation, Learning, and Optimization book series (ALO, volume 12)

Abstract

This chapter presents an overview of the decentralized POMDP (Dec- POMDP) framework. In a Dec-POMDP, a team of agents collaborates to maximize a global reward based on local information only. This means that agents do not observe a Markovian signal during execution and therefore the agents’ individual policies map fromhistories to actions. Searching for an optimal joint policy is an extremely hard problem: it is NEXP-complete. This suggests, assuming NEXP≠EXP, that any optimal solution method will require doubly exponential time in the worst case. This chapter focuses on planning for Dec-POMDPs over a finite horizon. It covers the forward heuristic search approach to solving Dec-POMDPs, as well as the backward dynamic programming approach. Also, it discusses how these relate to the optimal Q-value function of a Dec-POMDP. Finally, it provides pointers to other solution methods and further related topics.

Keywords

Multi Agent System Multiagent System Autonomous Agent International Joint Observation History 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Abdallah, S., Lesser, V.: Multiagent reinforcement learning and self-organization in a network of agents. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 172–179 (2007)Google Scholar
  2. Amato, C., Carlin, A., Zilberstein, S.: Bounded dynamic programming for decentralized POMDPs. In: Proc. of the AAMAS Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains, MSDM (2007)Google Scholar
  3. Amato, C., Dibangoye, J.S., Zilberstein, S.: Incremental policy generation for finite-horizon DEC-POMDPs. In: Proc. of the International Conference on Automated Planning and Scheduling, pp. 2–9 (2009)Google Scholar
  4. Amato, C., Bernstein, D.S., Zilberstein, S.: Optimizing fixed-size stochastic controllers for POMDPs and decentralized POMDPs. Autonomous Agents and Multi-Agent Systems 21(3), 293–320 (2010)CrossRefGoogle Scholar
  5. Aras, R., Dutech, A., Charpillet, F.: Mixed integer linear programming for exact finite-horizon planning in decentralized POMDPs. In: Proc. of the International Conference on Automated Planning and Scheduling (2007)Google Scholar
  6. Becker, R., Zilberstein, S., Lesser, V.: Decentralized Markov decision processes with event-driven interactions. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 302–309 (2004a)Google Scholar
  7. Becker, R., Zilberstein, S., Lesser, V., Goldman, C.V.: Solving transition independent decentralized Markov decision processes. Journal of Artificial Intelligence Research 22, 423–455 (2004b)MathSciNetzbMATHGoogle Scholar
  8. Becker, R., Lesser, V., Zilberstein, S.: Analyzing myopic approaches for multi-agent communication. In: Proc. of the International Conference on Intelligent Agent Technology, pp. 550–557 (2005)Google Scholar
  9. Bernstein, D.S., Givan, R., Immerman, N., Zilberstein, S.: The complexity of decentralized control of Markov decision processes. Mathematics of Operations Research 27(4), 819–840 (2002)MathSciNetzbMATHCrossRefGoogle Scholar
  10. Bernstein, D.S., Hansen, E.A., Zilberstein, S.: Bounded policy iteration for decentralized POMDPs. In: Proc. of the International Joint Conference on Artificial Intelligence, pp. 1287–1292 (2005)Google Scholar
  11. Bernstein, D.S., Amato, C., Hansen, E.A., Zilberstein, S.: Policy iteration for decentralized control of Markov decision processes. Journal of Artificial Intelligence Research 34, 89–132 (2009)MathSciNetzbMATHGoogle Scholar
  12. Boularias, A., Chaib-draa, B.: Exact dynamic programming for decentralized POMDPs with lossless policy compression. In: Proc. of the International Conference on Automated Planning and Scheduling (2008)Google Scholar
  13. Boutilier, C.: Planning, learning and coordination in multiagent decision processes. In: Proc. of the 6th Conference on Theoretical Aspects of Rationality and Knowledge, pp. 195–210 (1996)Google Scholar
  14. Boyan, J.A., Littman, M.L.: Packet routing in dynamically changing networks: A reinforcement learning approach. In: Advances in Neural Information Processing Systems, vol. 6, pp. 671–678 (1993)Google Scholar
  15. Buşoniu, L., Babuška, R., De Schutter, B.: A comprehensive survey of multi-agent reinforcement learning. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews 38(2), 156–172 (2008)CrossRefGoogle Scholar
  16. Carlin, A., Zilberstein, S.: Value-based observation compression for DEC-POMDPs. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 501–508 (2008)Google Scholar
  17. Chang, Y.H., Ho, T.: Mobilized ad-hoc networks: A reinforcement learning approach. In: Proceedings of the First International Conference on Autonomic Computing, pp. 240–247 (2004)Google Scholar
  18. Chang, Y.H., Ho, T., Kaelbling, L.P.: All learning is local: Multi-agent learning in global reward games. In: Advances in Neural Information Processing Systems, vol. 16 (2004)Google Scholar
  19. Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proc. of the National Conference on Artificial Intelligence, pp. 746–752 (1998)Google Scholar
  20. Cogill, R., Rotkowitz, M., Roy, B.V., Lall, S.: An approximate dynamic programming approach to decentralized control of stochastic systems. In: Proc. of the 2004 Allerton Conference on Communication, Control, and Computing (2004)Google Scholar
  21. Crites, R.H., Barto, A.G.: Elevator group control using multiple reinforcement learning agents. Machine Learning 33(2-3), 235–262 (1998)zbMATHCrossRefGoogle Scholar
  22. Dibangoye, J.S., Mouaddib, A.I., Chai-draa, B.: Point-based incremental pruning heuristic for solving finite-horizon DEC-POMDPs. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 569–576 (2009)Google Scholar
  23. Eker, B., Akın, H.L.: Using evolution strategies to solve DEC-POMDP problems. Soft Computing - A Fusion of Foundations, Methodologies and Applications (2008)Google Scholar
  24. Emery-Montemerlo, R., Gordon, G., Schneider, J., Thrun, S.: Approximate solutions for partially observable stochastic games with common payoffs. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 136–143 (2004)Google Scholar
  25. Emery-Montemerlo, R., Gordon, G., Schneider, J., Thrun, S.: Game theoretic control for robot teams. In: Proc. of the IEEE International Conference on Robotics and Automation, pp. 1175–1181 (2005)Google Scholar
  26. Goldman, C.V., Zilberstein, S.: Optimizing information exchange in cooperative multi-agent systems. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 137–144 (2003)Google Scholar
  27. Goldman, C.V., Zilberstein, S.: Decentralized control of cooperative systems: Categorization and complexity analysis. Journal of Artificial Intelligence Research 22, 143–174 (2004)MathSciNetzbMATHGoogle Scholar
  28. Goldman, C.V., Zilberstein, S.: Communication-based decomposition mechanisms for decentralized MDPs. Journal of Artificial Intelligence Research 32, 169–202 (2008)MathSciNetzbMATHGoogle Scholar
  29. Goldman, C.V., Allen, M., Zilberstein, S.: Learning to communicate in a decentralized environment. Autonomous Agents and Multi-Agent Systems 15(1), 47–90 (2007)CrossRefGoogle Scholar
  30. Guestrin, C., Lagoudakis, M., Parr, R.: Coordinated reinforcement learning. In: Proc. of the International Conference on Machine Learning, pp. 227–234 (2002)Google Scholar
  31. Hansen, E.A., Bernstein, D.S., Zilberstein, S.: Dynamic programming for partially observable stochastic games. In: Proc. of the National Conference on Artificial Intelligence, pp. 709–715 (2004)Google Scholar
  32. Kaisers, M., Tuyls, K.: Frequency adjusted multi-agent Q-learning. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 309–316 (2010)Google Scholar
  33. Kim, Y., Nair, R., Varakantham, P., Tambe, M., Yokoo, M.: Exploiting locality of interaction in networked distributed POMDPs. In: Proc. of the AAAI Spring Symposium on Distributed Plan and Schedule Management (2006)Google Scholar
  34. Kok, J.R., Vlassis, N.: Collaborative multiagent reinforcement learning by payoff propagation. Journal of Machine Learning Research 7, 1789–1828 (2006)MathSciNetzbMATHGoogle Scholar
  35. Koller, D., Pfeffer, A.: Representations and solutions for game-theoretic problems. Artificial Intelligence 94(1-2), 167–215 (1997)MathSciNetzbMATHCrossRefGoogle Scholar
  36. Koller, D., Megiddo, N., von Stengel, B.: Fast algorithms for finding randomized strategies in game trees. In: Proc. of the 26th ACM Symposium on Theory of Computing, pp. 750–759 (1994)Google Scholar
  37. Kumar, A., Zilberstein, S.: Constraint-based dynamic programming for decentralized POMDPs with structured interactions. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 561–568 (2009)Google Scholar
  38. Kumar, A., Zilberstein, S.: Anytime planning for decentralized POMDPs using expectation maximization. In: Proc. of Uncertainty in Artificial Intelligence (2010a)Google Scholar
  39. Kumar, A., Zilberstein, S.: Point-based backup for decentralized POMDPs: Complexity and new algorithms. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 1315–1322 (2010b)Google Scholar
  40. Madani, O., Hanks, S., Condon, A.: On the undecidability of probabilistic planning and infinite-horizon partially observable Markov decision problems. In: Proc. of the National Conference on Artificial Intelligence, pp. 541–548 (1999)Google Scholar
  41. Marecki, J., Gupta, T., Varakantham, P., Tambe, M., Yokoo, M.: Not all agents are equal: scaling up distributed POMDPs for agent networks. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 485–492 (2008)Google Scholar
  42. Mostafa, H., Lesser, V.: Offline planning for communication by exploiting structured interactions in decentralized MDPs. In: Proc. of 2009 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, pp. 193–200 (2009)Google Scholar
  43. Nair, R., Tambe, M., Marsella, S.: Role allocation and reallocation in multiagent teams: towards a practical analysis. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 552–559 (2003a)Google Scholar
  44. Nair, R., Tambe, M., Marsella, S.C.: Team Formation for Reformation in Multiagent Domains Like RoboCupRescue. In: Kaminka, G.A., Lima, P.U., Rojas, R. (eds.) RoboCup 2002: Robot Soccer World Cup VI, LNCS (LNAI), vol. 2752, pp. 150–161. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  45. Nair, R., Tambe, M., Yokoo, M., Pynadath, D.V., Marsella, S.: Taming decentralized POMDPs: Towards efficient policy computation for multiagent settings. In: Proc. of the International Joint Conference on Artificial Intelligence, pp. 705–711 (2003c)Google Scholar
  46. Nair, R., Roth, M., Yohoo, M.: Communication for improving policy computation in distributed POMDPs. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 1098–1105 (2004)Google Scholar
  47. Nair, R., Varakantham, P., Tambe, M., Yokoo, M.: Networked distributed POMDPs: A synthesis of distributed constraint optimization and POMDPs. In: Proc. of the National Conference on Artificial Intelligence, pp. 133–139 (2005)Google Scholar
  48. Oliehoek, F.A.: Value-based planning for teams of agents in stochastic partially observable environments. PhD thesis, Informatics Institute, University of Amsterdam (2010)Google Scholar
  49. Oliehoek, F.A., Vlassis, N.: Q-value functions for decentralized POMDPs. In: Proc. of The International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 833–840 (2007)Google Scholar
  50. Oliehoek, F.A., Spaan, M.T.J., Vlassis, N.: Dec-POMDPs with delayed communication. In: AAMAS Workshop on Multi-agent Sequential Decision Making in Uncertain Domains (2007)Google Scholar
  51. Oliehoek, F.A., Kooi, J.F., Vlassis, N.: The cross-entropy method for policy search in decentralized POMDPs. Informatica 32, 341–357 (2008a)zbMATHGoogle Scholar
  52. Oliehoek, F.A., Spaan, M.T.J., Vlassis, N.: Optimal and approximate Q-value functions for decentralized POMDPs. Journal of Artificial Intelligence Research 32, 289–353 (2008b)MathSciNetzbMATHGoogle Scholar
  53. Oliehoek, F.A., Spaan, M.T.J., Whiteson, S., Vlassis, N.: Exploiting locality of interaction in factored Dec-POMDPs. In: Proc. of The International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 517–524 (2008)Google Scholar
  54. Oliehoek, F.A., Whiteson, S., Spaan, M.T.J.: Lossless clustering of histories in decentralized POMDPs. In: Proc. of The International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 577–584 (2009)Google Scholar
  55. Oliehoek, F.A., Spaan, M.T.J., Dibangoye, J., Amato, C.: Heuristic search for identical payoff Bayesian games. In: Proc. of The International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 1115–1122 (2010)Google Scholar
  56. Ooi, J.M., Wornell, G.W.: Decentralized control of a multiple access broadcast channel: Performance bounds. In: Proc. of the 35th Conference on Decision and Control, pp. 293–298 (1996)Google Scholar
  57. Osborne, M.J., Rubinstein, A.: A Course in Game Theory. The MIT Press (1994)Google Scholar
  58. Pajarinen, J., Peltonen, J.: Efficient planning for factored infinite-horizon DEC-POMDPs. In: Proc. of the International Joint Conference on Artificial Intelligence (to appear, 2011)Google Scholar
  59. Paquet, S., Tobin, L., Chaib-draa, B.: An online POMDP algorithm for complex multiagent environments. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems (2005)Google Scholar
  60. Peshkin, L.: Reinforcement learning by policy search. PhD thesis, Brown University (2001)Google Scholar
  61. Peshkin, L., Kim, K.E., Meuleau, N., Kaelbling, L.P.: Learning to cooperate via policy search. In: Proc. of Uncertainty in Artificial Intelligence, pp. 307–314 (2000)Google Scholar
  62. Pynadath, D.V., Tambe, M.: The communicative multiagent team decision problem: Analyzing teamwork theories and models. Journal of Artificial Intelligence Research 16, 389–423 (2002)MathSciNetzbMATHGoogle Scholar
  63. Rabinovich, Z., Goldman, C.V., Rosenschein, J.S.: The complexity of multiagent systems: the price of silence. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 1102–1103 (2003)Google Scholar
  64. Roth, M., Simmons, R., Veloso, M.: Decentralized communication strategies for coordinated multi-agent policies. In: Parker, L.E., Schneider, F.E., Shultz, A.C. (eds.) Multi-Robot Systems. From Swarms to Intelligent Automata, vol. III, pp. 93–106. Springer, Heidelberg (2005a)CrossRefGoogle Scholar
  65. Roth, M., Simmons, R., Veloso, M.: Reasoning about joint beliefs for execution-time communication decisions. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 786–793 (2005b)Google Scholar
  66. Roth, M., Simmons, R., Veloso, M.: Exploiting factored representations for decentralized execution in multi-agent teams. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 467–463 (2007)Google Scholar
  67. Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn. Pearson Education (2003)Google Scholar
  68. Seuken, S., Zilberstein, S.: Improved memory-bounded dynamic programming for decentralized POMDPs. In: Proc. of Uncertainty in Artificial Intelligence (2007a)Google Scholar
  69. Seuken, S., Zilberstein, S.: Memory-bounded dynamic programming for DEC-POMDPs. In: Proc. of the International Joint Conference on Artificial Intelligence, pp. 2009–2015 (2007b)Google Scholar
  70. Seuken, S., Zilberstein, S.: Formal models and algorithms for decentralized decision making under uncertainty. Autonomous Agents and Multi-Agent Systems 17(2), 190–250 (2008)CrossRefGoogle Scholar
  71. Singh, S.P., Jaakkola, T., Jordan, M.I.: Learning without state-estimation in partially observable Markovian decision processes. In: Proc. of the International Conference on Machine Learning, pp. 284–292. Morgan Kaufmann (1994)Google Scholar
  72. Spaan, M.T.J., Gordon, G.J., Vlassis, N.: Decentralized planning under uncertainty for teams of communicating agents. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 249–256 (2006)Google Scholar
  73. Spaan, M.T.J., Oliehoek, F.A., Amato, C.: Scaling up optimal heuristic search in Dec-POMDPs via incremental expansion. In: Proc. of the International Joint Conference on Artificial Intelligence (to appear, 2011)Google Scholar
  74. Szer, D., Charpillet, F.: Point-based dynamic programming for DEC-POMDPs. In: Proc. of the National Conference on Artificial Intelligence (2006)Google Scholar
  75. Szer, D., Charpillet, F., Zilberstein, S.: MAA*: A heuristic search algorithm for solving decentralized POMDPs. In: Proc. of Uncertainty in Artificial Intelligence, pp. 576–583 (2005)Google Scholar
  76. Tuyls, K., Hoen, P.J., Vanschoenwinkel, B.: An evolutionary dynamical analysis of multi-agent learning in iterated games. Autonomous Agents and Multi-Agent Systems 12(1), 115–153 (2006)CrossRefGoogle Scholar
  77. Varakantham, P., Marecki, J., Yabu, Y., Tambe, M., Yokoo, M.: Letting loose a SPIDER on a network of POMDPs: Generating quality guaranteed policies. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems (2007)Google Scholar
  78. Varakantham, P., Young Kwak, J., Taylor, M.E., Marecki, J., Scerri, P., Tambe, M.: Exploiting coordination locales in distributed POMDPs via social model shaping. In: Proc. of the International Conference on Automated Planning and Scheduling (2009)Google Scholar
  79. Varshavskaya, P., Kaelbling, L.P., Rus, D.: Automated design of adaptive controllers for modular robots using reinforcement learning. International Journal of Robotics Research 27(3-4), 505–526 (2008)CrossRefGoogle Scholar
  80. Vlassis, N.: A Concise Introduction to Multiagent Systems and Distributed Artificial Intelligence. In: Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers (2007)Google Scholar
  81. Witwicki, S.J.: Abstracting influences for efficient multiagent coordination under uncertainty. PhD thesis, University of Michigan, Ann Arbor, Michigan, USA (2011)Google Scholar
  82. Witwicki, S.J., Durfee, E.H.: Influence-based policy abstraction for weakly-coupled Dec-POMDPs. In: Proc. of the International Conference on Automated Planning and Scheduling, pp. 185–192 (2010)Google Scholar
  83. Wu, F., Zilberstein, S., Chen, X.: Point-based policy generation for decentralized POMDPs. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 1307–1314 (2010a)Google Scholar
  84. Wu, F., Zilberstein, S., Chen, X.: Rollout sampling policy iteration for decentralized POMDPs. In: Proc. of Uncertainty in Artificial Intelligence (2010b)Google Scholar
  85. Wu, F., Zilberstein, S., Chen, X.: Trial-based dynamic programming for multi-agent planning. In: Proc. of the National Conference on Artificial Intelligence, pp. 908–914 (2010c)Google Scholar
  86. Wu, F., Zilberstein, S., Chen, X.: Online planning for multi-agent systems with bounded communication. Artificial Intelligence 175(2), 487–511 (2011)MathSciNetzbMATHCrossRefGoogle Scholar
  87. Wu, J., Durfee, E.H.: Mixed-integer linear programming for transition-independent decentralized MDPs. In: Proc. of the International Joint Conference on Autonomous Agents and Multi Agent Systems, pp. 1058–1060 (2006)Google Scholar
  88. Wunder, M., Littman, M.L., Babes, M.: Classes of multiagent Q-learning dynamics with epsilon-greedy exploration. In: Proc. of the International Conference on Machine Learning, pp. 1167–1174 (2010)Google Scholar
  89. Xuan, P., Lesser, V., Zilberstein, S.: Communication decisions in multi-agent cooperation: Model and experiments. In: Proc. of the International Conference on Autonomous Agents (2001)Google Scholar
  90. Zettlemoyer, L.S., Milch, B., Kaelbling, L.P.: Multi-agent filtering with infinitely nested beliefs. In: Advances in Neural Information Processing Systems, vol. 21 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.CSAIL, Massachusetts Institute of TechnologyCambridgeUS

Personalised recommendations

Cite chapter

Buy options