Bounded Planning in Passive POMDPs
Machine Learning
2012-07-03 v1 Artificial Intelligence
Machine Learning
Abstract
In Passive POMDPs actions do not affect the world state, but still incur costs. When the agent is bounded by information-processing constraints, it can only keep an approximation of the belief. We present a variational principle for the problem of maintaining the information which is most useful for minimizing the cost, and introduce an efficient and simple algorithm for finding an optimum.
Cite
@article{arxiv.1206.6405,
title = {Bounded Planning in Passive POMDPs},
author = {Roy Fox and Naftali Tishby},
journal= {arXiv preprint arXiv:1206.6405},
year = {2012}
}
Comments
Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)