CoChat

Sophisticated Inference

Open access
Friston, Karl, Da Costa, Lancelot, Hafner, Danijar, Hesp, Casper, Parr, Thomas · 2021 · Neural Computation
Cited by 117

The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.

Abstract

Active inference offers a first principle account of sentient behavior, from which special and important cases—for example, reinforcement learning, active learning, Bayes optimal inference, Bayes optimal design—can be derived. Active inference finesses the exploitation-exploration dilemma in relation to prior preferences by placing information gain on the same footing as reward or value. In brief, active inference replaces value functions with functionals of (Bayesian) beliefs, in the form of an expected (variational) free energy. In this letter, we consider a sophisticated kind of active inference using a recursive form of expected free energy. Sophistication describes the degree to which an agent has beliefs about beliefs. We consider agents with beliefs about the counterfactual consequences of action for states of affairs and beliefs about those latent states. In other words, we move from simply considering beliefs about “what would happen if I did that” to “what I would believe about what would happen if I did that.” The recursive form of the free energy functional effectively implements a deep tree search over actions and outcomes in the future. Crucially, this search is over sequences of belief states as opposed to states per se. We illustrate the competence of this scheme using numerical simulations of deep decision problems.

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_01351

Cites

32 of 32 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 32 references

Research works printed but not linked: 76

  1. 10.1162/089976698300017746 · DOI · Paper page
  2. Attias H., 2003, Proceedings of the 9th Int. Workshop on Artificial Intelligence and Statistics
  3. 10.3390/e17042432 · DOI · Paper page
  4. Barlow H., 1961, Sensory communication, 217
  5. 10.1068/p030123 · DOI
  6. Beal M. J., 2003, Variational algorithms for approximate Bayesian inference
  7. 10.1162/089976601753195969 · DOI · Paper page
  8. 10.1016/j.tics.2012.08.006 · DOI · Paper page
  9. 10.1162/0033553041502225 · DOI · Paper page
  10. Catal O., 2019, Bayesian policy selection using active inference
  11. Çatal O., 2020, Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing
  12. Çatal O., 2020, Deep active inference for autonomous robot navigation
  13. 10.1063/1.4905960 · DOI
  14. 10.1098/rstb.2007.2098 · DOI · Paper page
  15. 10.1111/1468-0262.00239 · DOI · Paper page
  16. 10.1103/PhysRevLett.99.100602 · DOI · Paper page
  17. Da Costa L., 2020, Active inference on discrete state-spaces: A synthesis
  18. Da Costa L., 2020, Natural selection finds natural gradient
  19. Da Costa L., 2020, The relationship between dynamic programming and active inference: The discrete, finite-horizon case
  20. 10.1016/j.neuron.2011.02.027 · DOI · Paper page
  21. 10.1162/neco.1993.5.4.613 · DOI · Paper page
  22. 10.1162/neco.1995.7.5.889 · DOI · Paper page
  23. 10.1371/journal.pone.0087619 · DOI · Paper page
  24. 10.1016/S0893-6080(99)00046-5 · DOI · Paper page
  25. Duff M. O., 2002, Optimal learning: Computational procedures for Bayes-adaptive Markov decision processes
  26. 10.1214/aoap/1026915623 · DOI
  27. 10.1162/neco_a_00999 · DOI · Paper page
  28. 10.1016/j.neubiorev.2017.04.009 · DOI · Paper page
  29. 10.1016/j.cobeha.2017.05.025 · DOI · Paper page
  30. 10.1023/A:1007425814087 · DOI · Paper page
  31. Ghavamzadeh M., 2016, Bayesian reinforcement learning: A survey
  32. Hafez-Kolahi H., 2019, Information bottleneck and its applications in deep learning
  33. 10.1109/TSSC.1966.300074 · DOI · Paper page
  34. 10.1162/0899766041336477 · DOI · Paper page
  35. Jaynes E. T., 1957, Physical Review Series II, 106, 620
  36. 10.1007/s00422-018-0753-2 · DOI · Paper page
  37. 10.2307/2226451 · DOI · Paper page
  38. 10.1073/pnas.1609094113 · DOI · Paper page
  39. 10.3390/e20080574 · DOI · Paper page
  40. Klyubin A. S., 2005, Proceedings of the IEEE Congress on Evolutionary Computation, 1:128
  41. 10.1371/journal.pcbi.1005753 · DOI
  42. 10.1146/annurev.ne.13.030190.001353 · DOI · Paper page
  43. MacKay D. J. C., 2003, Information theory, inference and learning algorithms
  44. Millidge B., 2019, Deep active inference as variational policy gradients
  45. 10.1038/s41562-017-0180-8 · DOI · Paper page
  46. 10.1152/jn.1987.57.1.162 · DOI · Paper page
  47. 10.1613/jair.3062 · DOI
  48. Osband I., 2019, Journal of Machine Learning Research, 20, 1
  49. Parr T., 2020, Philosophical Transactions of the Royal Society A, 378
  50. 10.1038/s41598-017-15249-0 · DOI · Paper page
  51. 10.1016/j.copsyc.2018.10.006 · DOI · Paper page
  52. Rikhye R. V., 2019, Memorize-generalize: An online algorithm for learning higher-order sequential structure with cloned hidden Markov models
  53. Ross S., 2008, Advances in neural information processing systems, 20
  54. 10.1371/journal.pcbi.1005768 · DOI · Paper page
  55. Ryan R., 1985, Intrinsic motivation and self-determination in human behavior
  56. 10.1109/IJCNN.1991.170605 · DOI · Paper page
  57. 10.1080/09540090600768658 · DOI · Paper page
  58. Schrittwieser J., 2019, Mastering Atari, go, chess and shogi by planning with a learned model
  59. 10.3389/fpsyg.2013.00710 · DOI · Paper page
  60. 10.7554/eLife.41703 · DOI · Paper page
  61. Sengupta, B. & Friston, K. (2018). How robust are deep neural networks? arXiv:1804.11313. · arXiv
  62. 10.1073/pnas.1505483112 · DOI · Paper page
  63. 10.1103/PhysRevLett.109.120604 · DOI · Paper page
  64. 10.1109/IJCNN.2016.7727309 · DOI · Paper page
  65. Sutton R. S., 1998, Reinforcement learning: An introduction
  66. Tishby N., 1999, Proceedings of the 37th Annual Allerton Conference on Communication, Control, and Computing, 368
  67. Tishby N., 2010, Perception-reason-action cycle: Models, algorithms and systems
  68. Tishby N., 2015, Deep learning and the information bottleneck principle
  69. Todorov E., 2008, Proceedings of the IEEE Conference on Decision and Control
  70. Toussaint M., 2006, Proceedings of the 23rd Int. Conf. on Machine Learning
  71. Tribus M., 1961, Thermodynamics and thermostatics: An introduction to energy, information and states of matter, with engineering applications
  72. Tschantz A., 2019, Scaling active inference
  73. van den Broek J. L., 2010, Uncertainty in Artificial Intelligence, 6, 1
  74. Von Neumann J., 1944, Theory of games and economic behavior
  75. Winn J., 2005, Journal of Machine Learning Research, 6, 661
  76. 10.1109/TIT.2005.850085 · DOI · Paper page

Cited by

See all 117

Metadata

Authors
Friston, K., Da Costa, L., Hafner, D., Hesp, C., & Parr, T.
Venue
Neural Computation
Published
2021-03
Volume
33
Issue
3
Pages
713-763
ISSN
  • 0899-7667 (ISSN-L)
  • 1530-888X
OpenAlex
W3033196763
Cited by
117
References
32
FWCI
10.98
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: Sophisticated Inference. https://app.cochat.ai/papers/10.1162/neco_a_01351
The paper
Friston, K., Da Costa, L., Hafner, D., Hesp, C., & Parr, T. (2021). Sophisticated Inference. Neural Computation. https://doi.org/10.1162/neco_a_01351

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.