A Possibilistic Model for Qualitative Sequential Decision Problems under Uncertainty in Partially Observable Environments
This work addresses a computational bottleneck in decision-making under uncertainty for AI systems, though it appears incremental as it adapts an existing possibilistic theory to POMDPs.
The authors tackled the problem of infinite belief state spaces in partially observable Markov decision processes (POMDPs) by proposing a qualitative counterpart using possibility distributions, resulting in a finite belief state space that is exponentially larger than the state space but avoids the classical obstacle of stochastic POMDPs.
In this article we propose a qualitative (ordinal) counterpart for the Partially Observable Markov Decision Processes model (POMDP) in which the uncertainty, as well as the preferences of the agent, are modeled by possibility distributions. This qualitative counterpart of the POMDP model relies on a possibilistic theory of decision under uncertainty, recently developed. One advantage of such a qualitative framework is its ability to escape from the classical obstacle of stochastic POMDPs, in which even with a finite state space, the obtained belief state space of the POMDP is infinite. Instead, in the possibilistic framework even if exponentially larger than the state space, the belief state space remains finite.