Bounded Planning in Passive POMDPs

Roy Fox, and Naftali Tishby

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