Improved Memory-Bounded Dynamic Programming for Decentralized POMDPs

Abstract

Memory-Bounded Dynamic Programming (MBDP) has proved extremely effective in solving decentralized POMDPs with large horizons. We generalize the algorithm and improve its scalability by reducing the complexity with respect to the number of observations from exponential to polynomial. We derive error bounds on solution quality with respect to this new approximation and analyze the convergence behavior. To evaluate the effectiveness of the improvements, we introduce a new, larger benchmark problem. Experimental results show that despite the high complexity of decentralized POMDPs, scalable solution techniques such as MBDP perform surprisingly well.

Cite

Text

Seuken and Zilberstein. "Improved Memory-Bounded Dynamic Programming for Decentralized POMDPs." Conference on Uncertainty in Artificial Intelligence, 2007.

Markdown

[Seuken and Zilberstein. "Improved Memory-Bounded Dynamic Programming for Decentralized POMDPs." Conference on Uncertainty in Artificial Intelligence, 2007.](https://mlanthology.org/uai/2007/seuken2007uai-improved/)

BibTeX

@inproceedings{seuken2007uai-improved,
  title     = {{Improved Memory-Bounded Dynamic Programming for Decentralized POMDPs}},
  author    = {Seuken, Sven and Zilberstein, Shlomo},
  booktitle = {Conference on Uncertainty in Artificial Intelligence},
  year      = {2007},
  pages     = {344-351},
  url       = {https://mlanthology.org/uai/2007/seuken2007uai-improved/}
}