Error-Bounded Approximations for Infinite-Horizon Discounted Decentralized POMDPs

@inproceedings{Dibangoye2014ErrorBoundedAF,
  title={Error-Bounded Approximations for Infinite-Horizon Discounted Decentralized POMDPs},
  author={Jilles Steeve Dibangoye and Olivier Buffet and François Charpillet},
  booktitle={ECML/PKDD},
  year={2014}
}
We address decentralized stochastic control problems represented as decentralized partially observable Markov decision processes (Dec-POMDPs). This formalism provides a general model for decision-making under uncertainty in cooperative, decentralized settings, but the worst-case complexity makes it difficult to solve optimally (NEXP-complete). Recent advances suggest recasting Dec-POMDPs into continuous-state and deterministic MDPs. In this form, however, states and actions are embedded into… CONTINUE READING
4 Extracted Citations
21 Extracted References
Similar Papers

Similar Papers

Loading similar papers…