mlsanityData to 7 Oct 2026

Deep Active Inference for Partially Observable MDPs

arXiv 2009.03622 ↗First posted 8 Sep 2020cs.LG cs.AI cs.NEcited by 20

Not on the map. Why?

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.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 2; 2023: 2; 2024: 7; 2025: 1; 2026: 1.

20 papers.

Sort:

By area:

  1. 2021Active Inference in Robotics and Artificial Agents: Survey and Challengescited by 52
  2. 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 35
  3. 2021Multimodal VAE Active Inference Controllercited by 21
  4. 2024R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Modelscited by 10
  5. 2021Active Inference for Stochastic Controlcited by 6
  6. 2021Active inference, Bayesian optimal design, and expected utilitycited by 6
  7. 2021Neuroscience-inspired perception-action in robotics: applying active inference for state estimation, control and self-perceptioncited by 5
  8. 2022Geometric Methods for Sampling, Optimisation, Inference and Adaptive Agentscited by 5
  9. 2023Deconstructing deep active inferencecited by 5
  10. 2022Learning Policies for Continuous Control via Transition Modelscited by 3
  11. 2021Deep Active Inference for Pixel-Based Discrete Control: Evaluation on the Car Racing Problemcited by 2
  12. 2024Navigating Autonomous Vehicle on Unmarked Roads with Diffusion-Based Motion Prediction and Active Inferencecited by 2
8 more
  1. 2024Object-centric proto-symbolic behavioural reasoning from pixelscited by 2
  2. 2024Coupled autoregressive active inference agents for control of multi-joint dynamical systemscited by 1
  3. 2024Structure learning with Temporal Gaussian Mixture for model-based Reinforcement Learningcited by 1
  4. 2024Free Energy Projective Simulation (FEPS): Active inference with interpretabilitycited by 1
  5. 2021Differentiable Generalised Predictive Codingcited by 0
  6. 2024Seeing Through Uncertainty: Free-Energy-Inspired Real-Time Adaptation for Robust Visual Navigationcited by 0
  7. 2025Prior preferences in active inference agents: soft, hard, and goal shapingcited by 0
  8. 2026Distributional Active Inferencecited by 0