Bounded Planning in Passive POMDPs

Roy Fox and Naftali Tishby

29th International Conference on Machine Learning (ICML), 2012

BibTeX

@conference{ Fox2012Bounded,
  Title = "Bounded Planning in Passive {POMDP}s",
  Author = "Roy Fox and Naftali Tishby",
  Booktitle = "29th International Conference on Machine Learning (ICML)",
  Year = "2012"
}

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.