On Solving a Stochastic Shortest-Path Markov Decision Process as Probabilistic Inference
Abstract
Previous work on planning as active inference addresses finite horizon problems and solutions valid for online planning. We propose solving the general Stochastic Shortest-Path Markov Decision Process (SSP MDP) as probabilistic inference. Furthermore, we discuss online and offline methods for planning under uncertainty. In an SSP MDP, the horizon is indefinite and unknown a priori. SSP MDPs generalize finite and infinite horizon MDPs and are widely used in the artificial intelligence community. Additionally, we highlight some of the differences between solving an MDP using dynamic programming approaches widely used in the artificial intelligence community and approaches used in the active inference community.
Cite
@article{arxiv.2109.05866,
title = {On Solving a Stochastic Shortest-Path Markov Decision Process as Probabilistic Inference},
author = {Mohamed Baioumy and Bruno Lacerda and Paul Duckworth and Nick Hawes},
journal= {arXiv preprint arXiv:2109.05866},
year = {2021}
}
Comments
Presented at the second International Workshop on Active Inference (IWAI 2021); 11 pages, 2 figures