CoChat

Active Inference: Demystified and Compared

Open access
Sajid, Noor, Ball, Philip J., Parr, Thomas, Friston, Karl J. · 2021 · Neural Computation
Cited by 145

The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.

Abstract

Active inference is a first principle account of how autonomous agents operate in dynamic, nonstationary environments. This problem is also considered in reinforcement learning, but limited work exists on comparing the two approaches on the same discrete-state environments. In this letter, we provide (1) an accessible overview of the discrete-state formulation of active inference, highlighting natural behaviors in active inference that are generally engineered in reinforcement learning, and (2) an explicit discrete-state comparison between active inference and reinforcement learning on an OpenAI gym baseline. We begin by providing a condensed overview of the active inference literature, in particular viewing the various natural behaviors of active inference agents through the lens of reinforcement learning. We show that by operating in a pure belief-based setting, active inference agents can carry out epistemic exploration—and account for uncertainty about their environment—in a Bayes-optimal fashion. Furthermore, we show that the reliance on an explicit reward signal in reinforcement learning is removed in active inference, where reward can simply be treated as another observation we have a preference over; even in the total absence of rewards, agent behaviors are learned through preference learning. We make these properties explicit by showing two scenarios in which active inference agents can infer behaviors in reward-free environments compared to both Q-learning and Bayesian model-based reinforcement learning agents and by placing zero prior preferences over rewards and learning the prior preferences over the observations corresponding to reward. We conclude by noting that this formalism can be applied to more complex settings (e.g., robotic arm movement, Atari games) if appropriate generative models can be formulated. In short, we aim to demystify the behavior of active inference agents by presenting an accessible discrete state-space and time formulation and demonstrate these behaviors in a OpenAI gym environment, alongside reinforcement learning agents.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1162/neco_a_01357

Cites

31 of 31 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 31 references

Research works printed but not linked: 60

  1. Al-Shedivat M., 2017, Continuous adaptation via meta-learning in nonstationary and competitive environments
  2. Attias H., 2003, AISTATS
  3. 10.1016/B978-0-12-398532-3.00007-5 · DOI
  4. Beal M. J., 2003, Variational algorithms for approximate Bayesian inference
  5. Beck J., 2012, Advances in neural information processing systems, 25, 3059
  6. Blau T., 2019, Bayesian curiosity for efficient exploration in reinforcement learning.
  7. 10.1080/01621459.2017.1285773 · DOI · Paper page
  8. 10.1016/j.tics.2012.08.006 · DOI · Paper page
  9. 10.1016/j.jmp.2017.09.004 · DOI · Paper page
  10. Burda Y., 2018, Exploration by random network distillation
  11. Camacho E. F., 2013, Model predictive control
  12. Cao F., 2012, Advances in neural information processing systems, 25, 73
  13. Cesa-Bianchi N., 2017, Advances in neural information processing systems, 25, 6284
  14. 10.1073/pnas.1512144113 · DOI · Paper page
  15. 10.1016/j.bpsc.2018.06.010 · DOI · Paper page
  16. Da Costa L., 2020, Active inference on discrete state-spaces: A synthesis
  17. 10.1016/j.neuron.2011.02.027 · DOI · Paper page
  18. Dearden R., 2013, Model-based Bayesian exploration
  19. Dearden R., 1998, Proceedings of the 15th National Conference on Artificial Intelligence, 761
  20. Foerster J. N., 2017, Learning with opponent-learning awareness
  21. 10.1016/j.neubiorev.2017.04.009 · DOI · Paper page
  22. 10.1162/neco.2007.19.12.3173 · DOI · Paper page
  23. 10.1007/s10994-012-5313-8 · DOI
  24. 10.1002/9781119159193.ch33 · DOI · Paper page
  25. 10.1146/annurev-psych-122414-033625 · DOI · Paper page
  26. 10.1561/2200000049 · DOI · Paper page
  27. Igl M., 2019, Advances in neural information processing systems, 32, 13978
  28. Igl M., 2018, Deep variational reinforcement learning for POMDPs
  29. Kolter J. Z., 2009, Proceedings of the 26th Annual International Conference on Machine Learning, 513, 10.1145/1553374.1553441 · DOI · Paper page
  30. Lee L., 2019, Efficient exploration via state marginal matching
  31. 10.1098/rsif.2013.0069 · DOI · Paper page
  32. Millidge B., 2020, Whence the expected free energy?
  33. Millidge B., 2020, On the relationship between active inference and control as inference
  34. Mnih V., 2016, Proceedings of the International Conference on Machine Learning, 1928
  35. Mnih V., 2013, Playing Atari with deep reinforcement learning
  36. Mohamed, S. & Rezende, D. J. (2015).Variational information maximisation for intrinsically motivated reinforcement learning. arXiv:1509.08731. · arXiv
  37. 10.3389/fnhum.2014.00160 · DOI · Paper page
  38. Ng A. Y., 2003, Shaping and policy search in reinforcement learning
  39. O'Donoghue B., 2020, Making sense of reinforcement learning and probabilistic inference
  40. O'Donoghue B., 2018, Proceedings of the International Conference on Machine Learning, 3836
  41. Osband I., 2016, Advances in neural information processing systems, 29, 4026
  42. Padakandla S., 2019, Reinforcement learning in non-stationary environments
  43. 10.1162/neco_a_01102 · DOI · Paper page
  44. 10.1007/s00213-019-05240-0 · DOI · Paper page
  45. Pathak D., 2017, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 16
  46. Rakelly K., 2019, Proceedings of the International Conference on Machine Learning, 5331
  47. Ross S., 2008, Advances in neural information processing systems, 20, 1225
  48. 10.1080/09540090600768658 · DOI · Paper page
  49. 10.1016/j.mehy.2014.12.007 · DOI · Paper page
  50. 10.7554/eLife.41703 · DOI · Paper page
  51. Sekar R., 2020, Planning to explore via self-supervised world models
  52. Sorg J., 2012, Variance-based rewards for approximate Bayesian reinforcement learning
  53. 10.1016/B978-1-55860-141-3.50030-4 · DOI · Paper page
  54. Sutton R. S., 1998, Introduction to reinforcement learning
  55. Sutton R. S., 2018, Reinforcement learning: An introduction
  56. Tijsma A. D., 2016, Proceedings of the IEEE Symposium Series on Computational Intelligence, 1
  57. Vermorel J., 2005, Proceedings of theEuropean Conference on Machine Learning, 437
  58. Watkins C. J. C. H., 1989, Learning from delayed rewards
  59. Wiering M., 1998, Proceedings of the Sixth International Conference on Simulation of Adaptive Behavior: From Animals to Animats, 6, 223
  60. Zintgraf L., 2019, Varibad: A very good method for Bayes-adaptive deep Rl via meta-learning

Cited by

See all 145

Metadata

Authors
Sajid, N., Ball, P. J., Parr, T., & Friston, K. J.
Venue
Neural Computation
Publisher
MIT Press
Published
2021-03
Volume
33
Issue
3
Pages
674-712
ISSN
  • 0899-7667 (ISSN-L)
  • 1530-888X
OpenAlex
W3003886363
Cited by
145
References
31
FWCI
8.65
Type
journal article
Language
en
Open access
green

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Active Inference: Demystified and Compared. https://app.cochat.ai/papers/10.1162/neco_a_01357
The paper
Sajid, N., Ball, P. J., Parr, T., & Friston, K. J. (2021). Active Inference: Demystified and Compared. Neural Computation. https://doi.org/10.1162/neco_a_01357

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.