# On Solving a Stochastic Shortest-Path Markov Decision Process as Probabilistic Inference

arXiv: https://arxiv.org/abs/2109.05866 · HTML: https://mlsanity.com/paper/2109.05866/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 34 references that are in the map.
- First posted on arXiv 13 Sep 2021.

## Builds on (most cited first, 6 of 6)

- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [Active inference on discrete state-spaces: a synthesis](https://mlsanity.com/paper/2001.07203/) (2020)
- [On the Relationship Between Active Inference and Control as Inference](https://mlsanity.com/paper/2006.12964/) (2020)
- [Active Inference and Behavior Trees for Reactive Action Planning and Execution in Robotics](https://mlsanity.com/paper/2011.09756/) (2020)
- [Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines](https://mlsanity.com/paper/1706.06643/) (2017)
- [Convex Hull Monte-Carlo Tree Search](https://mlsanity.com/paper/2003.04445/) (2020)

## Abstract (arXiv)

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.