Letting loose a SPIDER on a network of POMDPs: Generating quality guaranteed policies

Pradeep Varakantham, Janusz Marecki, Yuichi Yabu, Milind Tambe, Makoto Yokoo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

Distributed Partially Observable Markov Decision Problems (Distributed POMDPs) are a popular approach for modeling multi-agent systems acting in uncertain domains. Given the significant complexity of solving distributed POMDPs, particularly as we scale up the numbers of agents, one popular approach has focused on approximate solutions. Though this approach is efficient, the algorithms within this approach do not provide any guarantees on solution quality. A second less popular approach focuses on global optimality, but typical results are available only for two agents, and also at considerable computational cost. This paper overcomes the limitations of both these approaches by providing SPIDER, a novel combination of three key features for policy generation in distributed POMDPs: (i) it exploits agent interaction structure given a network of agents (i.e. allowing easier scale-up to larger number of agents); (ii) it uses a combination of heuristics to speedup policy search; and (iii) it allows quality guaranteed approximations, allowing a systematic tradeoff of solution quality for time. Experimental results show orders of magnitude improvement in performance when compared with previous global optimal algorithms.

Original languageEnglish
Title of host publicationAAMAS'07 - Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems
Pages822-829
Number of pages8
DOIs
Publication statusPublished - Dec 1 2007
Event6th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS'07 - Honolulu, HI, United States
Duration: May 14 2008May 18 2008

Publication series

NameProceedings of the International Conference on Autonomous Agents

Other

Other6th International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS'07
CountryUnited States
CityHonolulu, HI
Period5/14/085/18/08

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence
  • Computer Networks and Communications
  • Theoretical Computer Science

Fingerprint Dive into the research topics of 'Letting loose a SPIDER on a network of POMDPs: Generating quality guaranteed policies'. Together they form a unique fingerprint.

  • Cite this

    Varakantham, P., Marecki, J., Yabu, Y., Tambe, M., & Yokoo, M. (2007). Letting loose a SPIDER on a network of POMDPs: Generating quality guaranteed policies. In AAMAS'07 - Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems (pp. 822-829). [218] (Proceedings of the International Conference on Autonomous Agents). https://doi.org/10.1145/1329125.1329388