Bounded Planning in Passive POMDPs

06/27/2012
by   Roy Fox, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/28/2011

Information, Utility & Bounded Rationality

Perfectly rational decision-makers maximize expected utility, but crucia...
09/15/2019

Optimal robustness of passive discrete time systems

We construct optimally robust realizations of a given rational transfer ...
11/22/2019

Degree-Bounded Generalized Polymatroids and Approximating the Metric Many-Visits TSP

In the Bounded Degree Matroid Basis Problem, we are given a matroid and ...
02/13/2013

Constraining Influence Diagram Structure by Generative Planning: An Application to the Optimization of Oil Spill Response

This paper works through the optimization of a real world planning probl...
03/23/2022

Passive Haptic Rehearsal for Accelerated Piano Skill Acquisition

Passive haptic learning (PHL) uses vibrotactile stimulation to train pia...
12/06/2021

Inconsistent Planning: When in doubt, toss a coin!

One of the most widespread human behavioral biases is the present bias –...
11/05/2021

A space of goals: the cognitive geometry of informationally bounded agents

Traditionally, Euclidean geometry is treated by scientists as a priori a...