Applying Metric-Trees to Belief-Point POMDPs
Abstract
Recent developments in grid-based and point-based approximation algo- rithms for POMDPs have greatly improved the tractability of POMDP planning. These approaches operate on sets of belief points by individ- ually learning a value function for each point. In reality, belief points exist in a highly-structured metric simplex, but current POMDP algo- rithms do not exploit this property. This paper presents a new metric-tree algorithm which can be used in the context of POMDP planning to sort belief points spatially, and then perform fast value function updates over groups of points. We present results showing that this approach can re- duce computation in point-based POMDP algorithms for a wide range of problems.
Cite
Text
Pineau et al. "Applying Metric-Trees to Belief-Point POMDPs." Neural Information Processing Systems, 2003.Markdown
[Pineau et al. "Applying Metric-Trees to Belief-Point POMDPs." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/pineau2003neurips-applying/)BibTeX
@inproceedings{pineau2003neurips-applying,
title = {{Applying Metric-Trees to Belief-Point POMDPs}},
author = {Pineau, Joelle and Gordon, Geoffrey J. and Thrun, Sebastian},
booktitle = {Neural Information Processing Systems},
year = {2003},
pages = {759-766},
url = {https://mlanthology.org/neurips/2003/pineau2003neurips-applying/}
}