Bounded Dynamic Programming for Decentralized POMDPs
C. Amato, A. Carlin, and S. Zilberstein. Workshop at the International Conference on Autonomous Agents and Multi-Agent Systems, Honolulu, Hawaii, (2007)
Workshop at the International Conference on Autonomous Agents and Multi-Agent Systems
year
2007
comment
Bounded Dynamic Programming (BDP).
Bounds values when pruning additional policies in dynamic programming.
Given a problem and an error bound, the algorithm will return a solution within that bound when it is able to solve the problem.
---=note-separator=---
Bounded Dynamic Programming (BDP). Bounds values when pruning additional policies in dynamic programming. Given a problem and an error bound, the algorithm will return a solution within that bound when it is able to solve the problem.
Please log in to take part in the discussion (add own reviews or comments).
Cite this publication
More citation styles
- please select -
%0 Conference Paper
%1 Amato2007a
%A Amato, Christopher
%A Carlin, Alan
%A Zilberstein, Shlomo
%B Workshop at the International Conference on Autonomous Agents and Multi-Agent Systems
%C Honolulu, Hawaii
%D 2007
%K approximation, bottom-up, concurrent, dec-pomdp, decentralized, decision-tree, dp, finite-horizon, lim-com, nondet-outcomes, partial-obs
%T Bounded Dynamic Programming for Decentralized POMDPs
%U http://rbr.cs.umass.edu/shlomo/papers/ACZmsdm07.pdf
@inproceedings{Amato2007a,
added-at = {2020-05-24T20:36:48.000+0200},
address = {Honolulu, Hawaii},
author = {Amato, Christopher and Carlin, Alan and Zilberstein, Shlomo},
biburl = {https://www.bibsonomy.org/bibtex/26c1b95dd09ef3a536297be60d8aa80fc/marcondg},
booktitle = {Workshop at the International Conference on Autonomous Agents and Multi-Agent Systems},
comment = {Bounded Dynamic Programming (BDP).
Bounds values when pruning additional policies in dynamic programming.
Given a problem and an error bound, the algorithm will return a solution within that bound when it is able to solve the problem.
---=note-separator=---
Bounded Dynamic Programming (BDP). Bounds values when pruning additional policies in dynamic programming. Given a problem and an error bound, the algorithm will return a solution within that bound when it is able to solve the problem.},
interhash = {bca8a7c34e54ade7ab29d2612812fe78},
intrahash = {6c1b95dd09ef3a536297be60d8aa80fc},
keywords = {approximation, bottom-up, concurrent, dec-pomdp, decentralized, decision-tree, dp, finite-horizon, lim-com, nondet-outcomes, partial-obs},
timestamp = {2020-05-24T20:36:48.000+0200},
title = {Bounded Dynamic Programming for Decentralized {POMDP}s},
url = {http://rbr.cs.umass.edu/shlomo/papers/ACZmsdm07.pdf},
year = 2007
}