Bounded Planning in Passive POMDPs
This work addresses planning under information constraints for agents in passive environments, presenting an incremental improvement with a specific algorithmic solution.
The paper tackled the problem of bounded planning in Passive POMDPs, where actions incur costs without affecting the state, by developing a variational principle and an efficient algorithm to optimize information retention for cost minimization.
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.