mlsanityData to 7 Oct 2026

On the Relationship Between Active Inference and Control as Inference

arXiv 2006.12964 ↗First posted 23 Jun 2020cs.AI stat.MLcited by 42

Not on the map. Why?

Abstract (arXiv)

Active Inference (AIF) is an emerging framework in the brain sciences which suggests that biological agents act to minimise a variational bound on model evidence. Control-as-Inference (CAI) is a framework within reinforcement learning which casts decision making as a variational inference problem. While these frameworks both consider action selection through the lens of variational inference, their relationship remains unclear. Here, we provide a formal comparison between them and demonstrate that the primary difference arises from how value is incorporated into their respective generative models. In the context of this comparison, we highlight several ways in which these frameworks can inform one another.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 6; 2023: 5; 2024: 7; 2025: 5; 2026: 7.

42 papers.

Sort:

By area:

  1. 2021Active Inference in Robotics and Artificial Agents: Survey and Challengescited by 52
  2. 2022Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?cited by 45
  3. 2022pymdp: A Python library for active inference in discrete state spacescited by 39
  4. 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 35
  5. 2026Maximum Likelihood Reinforcement Learningcited by 29
  6. 2022Hybrid Predictive Coding: Inferring, Fast and Slowcited by 25
  7. 2022The Free Energy Principle for Perception and Action: A Deep Learning Perspectivecited by 24
  8. 2021Multimodal VAE Active Inference Controllercited by 21
  9. 2021Contrastive Active Inferencecited by 21
  10. 2023On efficient computation in active inferencecited by 15
  11. 2024Active Inference as a Model of Agencycited by 12
  12. 2021Understanding the Origin of Information-Seeking Exploration in Probabilistic Objectives for Controlcited by 10
30 more
  1. 2023A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learningcited by 9
  2. 2021Active Inference for Stochastic Controlcited by 6
  3. 2021Adaptation through prediction: multisensory active inference torque controlcited by 6
  4. 2021Chance-Constrained Active Inferencecited by 5
  5. 2021A Whole Brain Probabilistic Generative Model: Toward Realizing Cognitive Architectures for Developmental Robotscited by 4
  6. 2024Value of Information and Reward Specification in Active Inference and POMDPscited by 4
  7. 2021Online reinforcement learning with sparse rewards through an active inference capsulecited by 3
  8. 2021Towards Stochastic Fault-tolerant Control using Precision Learning and Active Inferencecited by 3
  9. 2022Successor Representation Active Inferencecited by 3
  10. 2023Habits and goals in synergy: a variational Bayesian framework for behaviorcited by 3
  11. 2021A Unified View of Algorithms for Path Planning Using Probabilistic Inference on Factor Graphscited by 1
  12. 2023Life-inspired Interoceptive Artificial Intelligence for Autonomous and Adaptive Agentscited by 1
  13. 2024Limitations of Agents Simulated by Predictive Modelscited by 1
  14. 2025Emergence of Goal-Directed Behaviors via Active Inference with Self-Priorcited by 1
  15. 2026Active Inference as a Convex Markov Decision Processcited by 1
  16. 2021On Solving a Stochastic Shortest-Path Markov Decision Process as Probabilistic Inferencecited by 0
  17. 2022Efficient search of active inference policy spaces using k-meanscited by 0
  18. 2024Deep hybrid models: infer and plan in a dynamic worldcited by 0
  19. 2024When in Doubt, Think Slow: Iterative Reasoning with Latent Imaginationcited by 0
  20. 2024Hybrid Recurrent Models Support Emergent Descriptions for Hierarchical Planning and Controlcited by 0
  21. 2024Learning in Hybrid Active Inference Modelscited by 0
  22. 2025A memory-based active inference model of DishBrain-like adaptive behaviourcited by 0
  23. 2025Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?cited by 0
  24. 2025Graph Distance as Surprise: Free Energy Minimization in Knowledge Graph Reasoningcited by 0
  25. 2025EcoNet: Multiagent Planning and Control Of Household Energy Resources Using Active Inferencecited by 0
  26. 2026Distributional Active Inferencecited by 0
  27. 2026Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifoldscited by 0
  28. 2026Expected Free Energy as Belief-Dependent Utility for rho-POMDPscited by 0
  29. 2026Generalised Bellman recurrence and three dualities in sequential decision-makingcited by 0
  30. 2026Active Inference as Context Acquisition for AI Agentscited by 0