# A free energy principle for a particular physics

arXiv: https://arxiv.org/abs/1906.10184 · HTML: https://mlsanity.com/paper/1906.10184/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2019.

## Built on by (most cited first, 30 of 40)

- [pymdp: A Python library for active inference in discrete state spaces](https://mlsanity.com/paper/2201.03904/) (2022)
- [Designing Ecosystems of Intelligence from First Principles](https://mlsanity.com/paper/2212.01354/) (2022)
- [On efficient computation in active inference](https://mlsanity.com/paper/2307.00504/) (2023)
- [Generative Emergent Communication: Large Language Model is a Collective World Model](https://mlsanity.com/paper/2501.00226/) (2024)
- [Expected Free Energy-based Planning as Variational Inference](https://mlsanity.com/paper/2504.14898/) (2025)
- [Applications of the Free Energy Principle to Machine Learning and Neuroscience](https://mlsanity.com/paper/2107.00140/) (2021)
- [Prior Preference Learning from Experts:Designing a Reward with Active Inference](https://mlsanity.com/paper/2101.08937/) (2021)
- [Object-based active inference](https://mlsanity.com/paper/2209.01258/) (2022)
- [Interpreting systems as solving POMDPs: a step towards a formal understanding of agency](https://mlsanity.com/paper/2209.01619/) (2022)
- [Active inference, Bayesian optimal design, and expected utility](https://mlsanity.com/paper/2110.04074/) (2021)
- [Hippocampal formation-inspired probabilistic generative model](https://mlsanity.com/paper/2103.07356/) (2021)
- [Interpreting Dynamical Systems as Bayesian Reasoners](https://mlsanity.com/paper/2112.13523/) (2021)
- [Constructive Approach to Bidirectional Influence between Qualia Structure and Language Emergence](https://mlsanity.com/paper/2409.09413/) (2024)
- [A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robots](https://mlsanity.com/paper/2103.08183/) (2021)
- [Realising Synthetic Active Inference Agents, Part I: Epistemic Objectives and Graphical Specification Language](https://mlsanity.com/paper/2306.08014/) (2023)
- [A "good regulator theorem" for embodied agents](https://mlsanity.com/paper/2508.06326/) (2025)
- [An active inference model of collective intelligence](https://mlsanity.com/paper/2104.01066/) (2021)
- [Successor Representation Active Inference](https://mlsanity.com/paper/2207.09897/) (2022)
- [Hybrid Life: Integrating Biological, Artificial, and Cognitive Systems](https://mlsanity.com/paper/2212.00285/) (2022)
- [Compositional Active Inference II: Polynomial Dynamics. Approximate Inference Doctrines](https://mlsanity.com/paper/2208.12173/) (2022)
- [A Neural Active Inference Model of Perceptual-Motor Learning](https://mlsanity.com/paper/2211.10419/) (2022)
- [Stochastic Surprisal: An inferential measurement of Free Energy in Neural Networks](https://mlsanity.com/paper/2302.05776/) (2023)
- [Predictive Minds: LLMs As Atypical Active Inference Agents](https://mlsanity.com/paper/2311.10215/) (2023)
- [Universal AI maximizes Variational Empowerment](https://mlsanity.com/paper/2502.15820/) (2025)
- [Self-orthogonalizing attractor neural networks emerging from the free energy principle](https://mlsanity.com/paper/2505.22749/) (2025)
- [Active Inference for Physical AI Agents -- An Engineering Perspective](https://mlsanity.com/paper/2603.20927/) (2026)
- [Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker](https://mlsanity.com/paper/2104.11798/) (2021)
- [A Mathematical Walkthrough and Discussion of the Free Energy Principle](https://mlsanity.com/paper/2108.13343/) (2021)
- [Bayesian sense of time in biological and artificial brains](https://mlsanity.com/paper/2201.05464/) (2022)
- [Separability, Contextuality, and the Quantum Frame Problem](https://mlsanity.com/paper/2304.10010/) (2023)

## Abstract (arXiv)

This monograph attempts a theory of every 'thing' that can be distinguished from other things in a statistical sense. The ensuing statistical independencies, mediated by Markov blankets, speak to a recursive composition of ensembles (of things) at increasingly higher spatiotemporal scales. This decomposition provides a description of small things; e.g., quantum mechanics - via the Schrodinger equation, ensembles of small things - via statistical mechanics and related fluctuation theorems, through to big things - via classical mechanics. These descriptions are complemented with a Bayesian mechanics for autonomous or active things. Although this work provides a formulation of every thing, its main contribution is to examine the implications of Markov blankets for self-organisation to nonequilibrium steady-state. In brief, we recover an information geometry and accompanying free energy principle that allows one to interpret the internal states of something as representing or making inferences about its external states. The ensuing Bayesian mechanics is compatible with quantum, statistical and classical mechanics and may offer a formal description of lifelike particles.