Bounded Planning in Passive POMDPs

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

Text

Fox and Tishby. "Bounded Planning in Passive POMDPs." International Conference on Machine Learning, 2012.

Markdown

[Fox and Tishby. "Bounded Planning in Passive POMDPs." International Conference on Machine Learning, 2012.](https://mlanthology.org/icml/2012/fox2012icml-bounded/)

BibTeX

@inproceedings{fox2012icml-bounded,
  title     = {{Bounded Planning in Passive POMDPs}},
  author    = {Fox, Roy and Tishby, Naftali},
  booktitle = {International Conference on Machine Learning},
  year      = {2012},
  url       = {https://mlanthology.org/icml/2012/fox2012icml-bounded/}
}