# Deep Active Inference

arXiv: https://arxiv.org/abs/1709.02341 · HTML: https://mlsanity.com/paper/1709.02341/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Sep 2017.

## Built on by (most cited first, 30 of 44)

- [Active Inference in Robotics and Artificial Agents: Survey and Challenges](https://mlsanity.com/paper/2112.01871/) (2021)
- [pymdp: A Python library for active inference in discrete state spaces](https://mlsanity.com/paper/2201.03904/) (2022)
- [The Free Energy Principle for Perception and Action: A Deep Learning Perspective](https://mlsanity.com/paper/2207.06415/) (2022)
- [An empirical evaluation of active inference in multi-armed bandits](https://mlsanity.com/paper/2101.08699/) (2021)
- [Exploration and preference satisfaction trade-off in reward-free learning](https://mlsanity.com/paper/2106.04316/) (2021)
- [Backprop-Free Reinforcement Learning with Active Neural Generative Coding](https://mlsanity.com/paper/2107.07046/) (2021)
- [Information is Power: Intrinsic Control via Information Capture](https://mlsanity.com/paper/2112.03899/) (2021)
- [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)
- [Interactive inference: a multi-agent model of cooperative joint actions](https://mlsanity.com/paper/2210.13113/) (2022)
- [Explore and Control with Adversarial Surprise](https://mlsanity.com/paper/2107.07394/) (2021)
- [Active Inference and Epistemic Value in Graphical Models](https://mlsanity.com/paper/2109.00541/) (2021)
- [Disentangling Shape and Pose for Object-Centric Deep Active Inference Models](https://mlsanity.com/paper/2209.09097/) (2022)
- [Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems](https://mlsanity.com/paper/2209.09174/) (2022)
- [Chance-Constrained Active Inference](https://mlsanity.com/paper/2102.08792/) (2021)
- [Deconstructing deep active inference](https://mlsanity.com/paper/2303.01618/) (2023)
- [Habits and goals in synergy: a variational Bayesian framework for behavior](https://mlsanity.com/paper/2304.05008/) (2023)
- [On Predictive planning and counterfactual learning in active inference](https://mlsanity.com/paper/2403.12417/) (2024)
- [Online reinforcement learning with sparse rewards through an active inference capsule](https://mlsanity.com/paper/2106.02390/) (2021)
- [Learning Policies for Continuous Control via Transition Models](https://mlsanity.com/paper/2209.08033/) (2022)
- [Active Inference Tree Search in Large POMDPs](https://mlsanity.com/paper/2103.13860/) (2021)
- [Goal-Directed Planning by Reinforcement Learning and Active Inference](https://mlsanity.com/paper/2106.09938/) (2021)
- [Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problem](https://mlsanity.com/paper/2109.04155/) (2021)
- [A Neural Active Inference Model of Perceptual-Motor Learning](https://mlsanity.com/paper/2211.10419/) (2022)
- [Free Energy Projective Simulation (FEPS): Active inference with interpretability](https://mlsanity.com/paper/2411.14991/) (2024)
- [The Missing Reward: Active Inference in the Era of Experience](https://mlsanity.com/paper/2508.05619/) (2025)
- [Realising Active Inference in Variational Message Passing: the Outcome-blind Certainty Seeker](https://mlsanity.com/paper/2104.11798/) (2021)
- [Learning Generative Models for Active Inference using Tensor Networks](https://mlsanity.com/paper/2208.08713/) (2022)
- [Coupled autoregressive active inference agents for control of multi-joint dynamical systems](https://mlsanity.com/paper/2410.10415/) (2024)
- [An Active Inference perspective on Neurofeedback Training](https://mlsanity.com/paper/2505.03308/) (2025)

## Abstract (arXiv)

This work combines the free energy principle from cognitive neuroscience and the ensuing active inference dynamics with recent advances in variational inference in deep generative models, and evolution strategies to introduce the "deep active inference" agent. This agent minimises a variational free energy bound on the average surprise of its sensations, which is motivated by a homeostatic argument. It does so by optimising the parameters of a generative latent variable model of its sensory inputs, together with a variational density approximating the posterior distribution over the latent variables, given its observations, and by acting on its environment to actively sample input that is likely under this generative model. The internal dynamics of the agent are implemented using deep and recurrent neural networks, as used in machine learning, making the deep active inference agent a scalable and very flexible class of active inference agent. Using the mountain car problem, we show how goal directed behaviour can be implemented by defining appropriate priors on the latent states in the agent's model. Furthermore, we show that the deep active inference agent can learn a generative model of the environment, which can be sampled from to understand the agent's beliefs about the environment and its interaction therewith.