Learning Perception and Planning with Deep Active Inference
Not on the map. Why?
Abstract (arXiv)
Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiments are limited to predefined, often discrete, state spaces. In this paper we use recent advances in deep learning to learn the state space and approximate the necessary probability distributions to engage in active inference.
Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jan 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 8; 2022: 5; 2023: 2; 2024: 2; 2025: 2.
19 papers.
Sort:
By area:
- 2022pymdp: A Python library for active inference in discrete state spacescited by 39
- 2022The Free Energy Principle for Perception and Action: A Deep Learning Perspectivecited by 24
- 2022Designing Ecosystems of Intelligence from First Principlescited by 23
- 2021Contrastive Active Inferencecited by 21
- 2021Branching Time Active Inference: the theory and its generalitycited by 15
- 2023On efficient computation in active inferencecited by 15
- 2021Exploration and preference satisfaction trade-off in reward-free learningcited by 12
- 2021Branching Time Active Inference: empirical study and complexity class analysiscited by 9
- 2021Prior Preference Learning from Experts:Designing a Reward with Active Inferencecited by 8
- 2021LatentSLAM: unsupervised multi-sensor representation learning for localization and mappingcited by 5
- 2022Learning Policies for Continuous Control via Transition Modelscited by 3
- 2021Branching Time Active Inference with Bayesian Filteringcited by 2
7 more
- 2022Multi-Modal and Multi-Factor Branching Time Active Inferencecited by 2
- 2023Sophisticated Learning: A novel algorithm for active learning during model-based planningcited by 2
- 2025The Missing Reward: Active Inference in the Era of Experiencecited by 2
- 2024Free Energy Projective Simulation (FEPS): Active inference with interpretabilitycited by 1
- 2021Differentiable Generalised Predictive Codingcited by 0
- 2024Environment-Centric Active Inferencecited by 0
- 2025A memory-based active inference model of DishBrain-like adaptive behaviourcited by 0
- 2025A memory-based active inference model of DishBrain-like adaptive behaviour9 Aug 2025
- 2025The Missing Reward: Active Inference in the Era of Experience7 Aug 2025
- 2024Free Energy Projective Simulation (FEPS): Active inference with interpretability22 Nov 2024
- 2024Environment-Centric Active Inference23 Aug 2024
- 2023Sophisticated Learning: A novel algorithm for active learning during model-based planning15 Aug 2023
- 2023On efficient computation in active inference2 Jul 2023
- 2022Designing Ecosystems of Intelligence from First Principles2 Dec 2022
- 2022Learning Policies for Continuous Control via Transition Models16 Sep 2022
- 2022The Free Energy Principle for Perception and Action: A Deep Learning Perspective13 Jul 2022
- 2022Multi-Modal and Multi-Factor Branching Time Active Inference24 Jun 2022
- 2022pymdp: A Python library for active inference in discrete state spaces11 Jan 2022
- 2021Branching Time Active Inference with Bayesian Filtering14 Dec 2021
7 more
- 2021Differentiable Generalised Predictive Coding2 Dec 2021
- 2021Branching Time Active Inference: empirical study and complexity class analysis22 Nov 2021
- 2021Branching Time Active Inference: the theory and its generality22 Nov 2021
- 2021Contrastive Active Inference19 Oct 2021
- 2021Exploration and preference satisfaction trade-off in reward-free learning8 Jun 2021
- 2021LatentSLAM: unsupervised multi-sensor representation learning for localization and mapping7 May 2021
- 2021Prior Preference Learning from Experts:Designing a Reward with Active Inference22 Jan 2021
- 2022pymdp: A Python library for active inference in discrete state spacescited by 39
- 2022The Free Energy Principle for Perception and Action: A Deep Learning Perspectivecited by 24
- 2022Designing Ecosystems of Intelligence from First Principlescited by 23
- 2021Contrastive Active Inferencecited by 21
- 2021Branching Time Active Inference: the theory and its generalitycited by 15
- 2023On efficient computation in active inferencecited by 15
- 2021Branching Time Active Inference: empirical study and complexity class analysiscited by 9
- 2021LatentSLAM: unsupervised multi-sensor representation learning for localization and mappingcited by 5
- 2022Learning Policies for Continuous Control via Transition Modelscited by 3
- 2021Branching Time Active Inference with Bayesian Filteringcited by 2
- 2022Multi-Modal and Multi-Factor Branching Time Active Inferencecited by 2
- 2023Sophisticated Learning: A novel algorithm for active learning during model-based planningcited by 2
12 most cited of 16 All 16 (JSON)
- 2025A memory-based active inference model of DishBrain-like adaptive behaviour9 Aug 2025
- 2024Free Energy Projective Simulation (FEPS): Active inference with interpretability22 Nov 2024
- 2024Environment-Centric Active Inference23 Aug 2024
- 2023Sophisticated Learning: A novel algorithm for active learning during model-based planning15 Aug 2023
- 2023On efficient computation in active inference2 Jul 2023
- 2022Designing Ecosystems of Intelligence from First Principles2 Dec 2022
- 2022Learning Policies for Continuous Control via Transition Models16 Sep 2022
- 2022The Free Energy Principle for Perception and Action: A Deep Learning Perspective13 Jul 2022
- 2022Multi-Modal and Multi-Factor Branching Time Active Inference24 Jun 2022
- 2022pymdp: A Python library for active inference in discrete state spaces11 Jan 2022
- 2021Branching Time Active Inference with Bayesian Filtering14 Dec 2021
- 2021Differentiable Generalised Predictive Coding2 Dec 2021
12 newest of 16 All 16 (JSON)