# Deep Active Inference for Partially Observable MDPs

arXiv: https://arxiv.org/abs/2009.03622 · HTML: https://mlsanity.com/paper/2009.03622/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2020.

## Built on by (most cited first, 20 of 20)

- [Active Inference in Robotics and Artificial Agents: Survey and Challenges](https://mlsanity.com/paper/2112.01871/) (2021)
- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [Multimodal VAE Active Inference Controller](https://mlsanity.com/paper/2103.04412/) (2021)
- [R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models](https://mlsanity.com/paper/2409.14216/) (2024)
- [Active Inference for Stochastic Control](https://mlsanity.com/paper/2108.12245/) (2021)
- [Active inference, Bayesian optimal design, and expected utility](https://mlsanity.com/paper/2110.04074/) (2021)
- [Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perception](https://mlsanity.com/paper/2105.04261/) (2021)
- [Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agents](https://mlsanity.com/paper/2203.10592/) (2022)
- [Deconstructing deep active inference](https://mlsanity.com/paper/2303.01618/) (2023)
- [Learning Policies for Continuous Control via Transition Models](https://mlsanity.com/paper/2209.08033/) (2022)
- [Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problem](https://mlsanity.com/paper/2109.04155/) (2021)
- [Navigating Autonomous Vehicle on Unmarked Roads with Diffusion-Based Motion Prediction and Active Inference](https://mlsanity.com/paper/2406.00211/) (2024)
- [Free Energy Projective Simulation (FEPS): Active inference with interpretability](https://mlsanity.com/paper/2411.14991/) (2024)
- [Object-centric proto-symbolic behavioural reasoning from pixels](https://mlsanity.com/paper/2411.17438/) (2024)
- [Coupled autoregressive active inference agents for control of multi-joint dynamical systems](https://mlsanity.com/paper/2410.10415/) (2024)
- [Structure learning with Temporal Gaussian Mixture for model-based Reinforcement Learning](https://mlsanity.com/paper/2411.11511/) (2024)
- [Prior preferences in active inference agents: soft, hard, and goal shaping](https://mlsanity.com/paper/2512.03293/) (2025)
- [Differentiable Generalised Predictive Coding](https://mlsanity.com/paper/2112.03378/) (2021)
- [Seeing Through Uncertainty: Free-Energy-Inspired Real-Time Adaptation for Robust Visual Navigation](https://mlsanity.com/paper/2403.01977/) (2024)
- [Distributional Active Inference](https://mlsanity.com/paper/2601.20985/) (2026)

## Abstract (arXiv)

Deep active inference has been proposed as a scalable approach to perception and action that deals with large policy and state spaces. However, current models are limited to fully observable domains. In this paper, we describe a deep active inference model that can learn successful policies directly from high-dimensional sensory inputs. The deep learning architecture optimizes a variant of the expected free energy and encodes the continuous state representation by means of a variational autoencoder. We show, in the OpenAI benchmark, that our approach has comparable or better performance than deep Q-learning, a state-of-the-art deep reinforcement learning algorithm.