# Exploiting Causality for Selective Belief Filtering in Dynamic Bayesian Networks (Extended Abstract)

arXiv: https://arxiv.org/abs/1907.05850 · HTML: https://mlsanity.com/paper/1907.05850/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2019.

## Built on by (most cited first, 7 of 7)

- [Conditional Mutual Information for Disentangled Representations in Reinforcement Learning](https://mlsanity.com/paper/2305.14133/) (2023)
- [A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning](https://mlsanity.com/paper/2210.05448/) (2022)
- [Revisiting the Gumbel-Softmax in MADDPG](https://mlsanity.com/paper/2302.11793/) (2023)
- [Integrating Counterfactual Simulations with Language Models for Explaining Multi-Agent Behaviour](https://mlsanity.com/paper/2505.17801/) (2025)
- [Optimal Clustering with Dependent Costs in Bayesian Networks](https://mlsanity.com/paper/2308.03970/) (2023)
- [A Stable Distance Persistence Homology for Dynamic Bayesian Network Clustering](https://mlsanity.com/paper/2605.11226/) (2026)
- [Divide-and-Remember: Recursive Action-Relevant Memory for Long-Horizon VLA Policies](https://mlsanity.com/paper/2610.00982/) (2026)

## Abstract (arXiv)

Dynamic Bayesian networks (DBNs) are a general model for stochastic processes with partially observed states. Belief filtering in DBNs is the task of inferring the belief state (i.e. the probability distribution over process states) based on incomplete and uncertain observations. In this article, we explore the idea of accelerating the filtering task by automatically exploiting causality in the process. We consider a specific type of causal relation, called passivity, which pertains to how state variables cause changes in other variables. We present the Passivity-based Selective Belief Filtering (PSBF) method, which maintains a factored belief representation and exploits passivity to perform selective updates over the belief factors. PSBF is evaluated in both synthetic processes and a simulated multi-robot warehouse, where it outperformed alternative filtering methods by exploiting passivity.