Sophisticated Inference
Open accessThe 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.
Integrity signals
Registry
Cites
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.
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
Prospect Theory: An Analysis of Decision under Risk
Kahneman, D., & Tversky, A. (1979) · Econometrica · doi:10.2307/1914185 · Cited by 48,524
Kass, R. E., & Raftery, A. E. (1995) · Journal of the American Statistical Association · doi:10.1080/01621459.1995.10476572 · Cited by 12,558
Continuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782
Statistical Decision Theory and Bayesian Analysis
Berger, J. O. (1985) · Springer Series in Statistics · doi:10.1007/978-1-4757-4286-2 · Cited by 7,722
THOMPSON, W. R. (1933) · Biometrika · doi:10.1093/biomet/25.3-4.285 · Cited by 2,712
On a measure of the information provided by an experiment
Lindley, D. V. (1956) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177728069 · Cited by 1,509
Toward a modern theory of adaptive networks: Expectation and prediction.
Sutton, R. S., & Barto, A. G. (1981) · Psychological Review · doi:10.1037/0033-295x.88.2.135 · Cited by 1,450 · cited 2×
“We also take the opportunity to survey the repertoire of existing schemes that fall under the Bayesian mechanics of active inference; including, expected utility theory (Von Neumann and Morgenstern, 1944), Bayesian decision theory (Berger, 2011), optimal Bayesian design (Lindley, 1956), reinforcement learning (Sutton…”
BackgroundBayesian surprise attracts human attention
Itti, L., & Baldi, P. (2009) · Vision Research · doi:10.1016/j.visres.2008.09.007 · Cited by 1,224
Information-based objective functions for active data selection
MacKay, D. J. C. (1992) · Neural Computation · doi:10.1162/neco.1992.4.4.590 · Cited by 1,221
Active inference: a process theory
Friston, K., FitzGerald, T., Rigoli, F., Schwartenbeck, P., & Pezzulo, G. (2017) · Neural Computation · doi:10.1162/neco_a_00912 · Cited by 1,156
Self-citationOn the theory of dynamic programming
Bellman, R. (1952) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.38.8.716 · Cited by 998
Optimal control of Markov processes with incomplete state information
Åström, K. J. (1965) · Journal of Mathematical Analysis and Applications · doi:10.1016/0022-247x(65)90154-x · Cited by 854 · cited 1×
“Sophisticated inference recovers Bayes-adaptive reinforcement learning (Åström, 1965; Ghavamzadeh, Mannor, Pineau, & Tamar, 2016; Ross, Chaibdraa, & Pineau, 2008) in the zero temperature limit.”
What is intrinsic motivation? A typology of computational approaches
Oudeyer, P.-Y. (2007) · Frontiers in Neurorobotics · doi:10.3389/neuro.12.006.2007 · Cited by 811
Friston, K. (2013) · Journal of The Royal Society Interface · doi:10.1098/rsif.2013.0475 · Cited by 754 · cited 8×
“…is, on statistical manifolds (Da Costa, Parr, Sengupta, et al., 2020), there is no need for sampling or random searches; the optimal paths are instead evaluated by propagating beliefs or probability distributions into the future to find the path of least variational free energy (Friston, 2013).”
BackgroundInfluentialSelf-citationFormal theory of creativity, fun, and intrinsic motivation (1990–2010)
Schmidhuber, J. (2010) · IEEE Transactions on Autonomous Mental Development · doi:10.1109/tamd.2010.2056368 · Cited by 747
Active inference and epistemic value
Friston, K., Rigoli, F., Ognibene, D., Mathys, C., Fitzgerald, T., & Pezzulo, G. (2015) · Cognitive Neuroscience · doi:10.1080/17588928.2015.1020053 · Cited by 731
Self-citationFriston, K., FitzGerald, T., Rigoli, F., Schwartenbeck, P., ODoherty, J., & Pezzulo, G. (2016) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2016.06.022 · Cited by 674
Self-citation(2005) · Edinburgh Research Explorer (University of Edinburgh) · doi:10.5555/1046920.1088695 · Cited by 650
Hohwy, J. (2016) · Noûs · doi:10.1111/nous.12062 · Cited by 578
The graphical brain: Belief propagation and active inference
Friston, K. J., Parr, T., & de Vries, B. (2017) · Network Neuroscience · doi:10.1162/netn_a_00018 · Cited by 415
Self-citationTowards a mathematical theory of cortical micro-circuits
George, D., & Hawkins, J. (2009) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1000532 · Cited by 404 · cited 1×
“One could also call on a related symmetry—namely, a hierarchical separation of temporal scales in deep models, where one Markov decision process is placed on top of another (Friston, Rosch, et al., 2017; George & Hawkins, 2009; Hesp, Smith, et al., 2019; Rikhye et al., 2019).”
BackgroundBarto, A., Mirolli, M., & Baldassarre, G. (2013) · Frontiers in Psychology · doi:10.3389/fpsyg.2013.00907 · Cited by 397 · cited 5×
“One can illustrate the minimization of expected free energy in terms of curiosity and novelty (Barto et al., 2013; Schmidhuber, 2006) by simulating a rat that has never been exposed to the maze previously.”
BackgroundInfluentialGeneral duality between optimal control and estimation
Todorov, E. (2008) · 2008 47th IEEE Conference on Decision and Control · doi:10.1109/cdc.2008.4739438 · Cited by 248
Deeply Felt Affect: The Emergence of Valence in Deep Active Inference
Hesp, C., Smith, R., Parr, T., Allen, M., Friston, K. J., & Ramstead, M. J. D. (2021) · Neural Computation · doi:10.1162/neco_a_01341 · Cited by 246
Self-citationGeneralised free energy and active inference
Parr, T., & Friston, K. J. (2019) · Biological Cybernetics · doi:10.1007/s00422-019-00805-w · Cited by 236 · cited 2×
“This optimization can be cast as minimizing a (generalized) free energy functional F[Q(s, π )] of the approximate posterior (Parr & Friston, 2019b).”
BackgroundSelf-citationA free energy principle for a particular physics
Friston, K. (2019) · arXiv · doi:10.48550/arxiv.1906.10184 · Cited by 222
Self-citationAn information-theoretic approach to curiosity-driven reinforcement learning
Still, S., & Precup, D. (2012) · Theory in Biosciences · doi:10.1007/s12064-011-0142-z · Cited by 165 · cited 1×
“In the current setting, we could replace information distance (Crooks, 2007; Kim, 2018) by information gain (Lindley, 1956; MacKay, 1992; Still & Precup, 2012).”
BackgroundPlanning to be surprised: optimal bayesian exploration in dynamic environments
Sun, Y., Gomez, F., & Schmidhuber, J. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-22887-2_5 · Cited by 134 · cited 2×
“This is mathematically the same as expected Bayesian surprise and mutual information that underwrites salience in visual search (Itti and Baldi, 2009; Sun et al., 2011) and the organisation of our visual apparatus (Barlow, 1961; Barlow, 1974; Linsker, 1990; Optican and Richmond, 1987).”
BackgroundNeuronal message passing using mean-field, bethe, and marginal approximations
Parr, T., Markovic, D., Kiebel, S. J., & Friston, K. J. (2019) · Scientific Reports · doi:10.1038/s41598-018-38246-3 · Cited by 128
Self-citationUeltzhöffer, K. (2018) · Biological Cybernetics · doi:10.1007/s00422-018-0785-7 · Cited by 98 · cited 3×
“For example, Ueltzhöffer (2018) parameterized both the generative model and approximate posterior with function approximators, using evolutionary schemes to minimize variational free energy when gradients were not available.”
MethodInfluentialAutomatic and controlled processing in the corticocerebellar system
Ramnani, N. (2014) · Progress in Brain Research · doi:10.1016/b978-0-444-63356-9.00010-8 · Cited by 70 · cited 2×
“However, it might be the case that certain brain structures learn to infer; for example, the cerebellum might learn from inferential processes implemented by the cerebral cortex (Doya, 1999; Ramnani, 2014).”
BackgroundA Multi-scale View of the Emergent Complexity of Life: A Free-Energy Proposal
Hesp, C., Ramstead, M., Constant, A., Badcock, P., Kirchhoff, M., & Friston, K. (2019) · Springer Proceedings in Complexity · doi:10.1007/978-3-030-00075-2_7 · Cited by 63
Self-citation
Research works printed but not linked: 76
- 10.1162/089976698300017746 · DOI · Paper page
- Attias H., 2003, Proceedings of the 9th Int. Workshop on Artificial Intelligence and Statistics
- 10.3390/e17042432 · DOI · Paper page
- Barlow H., 1961, Sensory communication, 217
- 10.1068/p030123 · DOI
- Beal M. J., 2003, Variational algorithms for approximate Bayesian inference
- 10.1162/089976601753195969 · DOI · Paper page
- 10.1016/j.tics.2012.08.006 · DOI · Paper page
- 10.1162/0033553041502225 · DOI · Paper page
- Catal O., 2019, Bayesian policy selection using active inference
- Çatal O., 2020, Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing
- Çatal O., 2020, Deep active inference for autonomous robot navigation
- 10.1063/1.4905960 · DOI
- 10.1098/rstb.2007.2098 · DOI · Paper page
- 10.1111/1468-0262.00239 · DOI · Paper page
- 10.1103/PhysRevLett.99.100602 · DOI · Paper page
- Da Costa L., 2020, Active inference on discrete state-spaces: A synthesis
- Da Costa L., 2020, Natural selection finds natural gradient
- Da Costa L., 2020, The relationship between dynamic programming and active inference: The discrete, finite-horizon case
- 10.1016/j.neuron.2011.02.027 · DOI · Paper page
- 10.1162/neco.1993.5.4.613 · DOI · Paper page
- 10.1162/neco.1995.7.5.889 · DOI · Paper page
- 10.1371/journal.pone.0087619 · DOI · Paper page
- 10.1016/S0893-6080(99)00046-5 · DOI · Paper page
- Duff M. O., 2002, Optimal learning: Computational procedures for Bayes-adaptive Markov decision processes
- 10.1214/aoap/1026915623 · DOI
- 10.1162/neco_a_00999 · DOI · Paper page
- 10.1016/j.neubiorev.2017.04.009 · DOI · Paper page
- 10.1016/j.cobeha.2017.05.025 · DOI · Paper page
- 10.1023/A:1007425814087 · DOI · Paper page
- Ghavamzadeh M., 2016, Bayesian reinforcement learning: A survey
- Hafez-Kolahi H., 2019, Information bottleneck and its applications in deep learning
- 10.1109/TSSC.1966.300074 · DOI · Paper page
- 10.1162/0899766041336477 · DOI · Paper page
- Jaynes E. T., 1957, Physical Review Series II, 106, 620
- 10.1007/s00422-018-0753-2 · DOI · Paper page
- 10.2307/2226451 · DOI · Paper page
- 10.1073/pnas.1609094113 · DOI · Paper page
- 10.3390/e20080574 · DOI · Paper page
- Klyubin A. S., 2005, Proceedings of the IEEE Congress on Evolutionary Computation, 1:128
- 10.1371/journal.pcbi.1005753 · DOI
- 10.1146/annurev.ne.13.030190.001353 · DOI · Paper page
- MacKay D. J. C., 2003, Information theory, inference and learning algorithms
- Millidge B., 2019, Deep active inference as variational policy gradients
- 10.1038/s41562-017-0180-8 · DOI · Paper page
- 10.1152/jn.1987.57.1.162 · DOI · Paper page
- 10.1613/jair.3062 · DOI
- Osband I., 2019, Journal of Machine Learning Research, 20, 1
- Parr T., 2020, Philosophical Transactions of the Royal Society A, 378
- 10.1038/s41598-017-15249-0 · DOI · Paper page
- 10.1016/j.copsyc.2018.10.006 · DOI · Paper page
- Rikhye R. V., 2019, Memorize-generalize: An online algorithm for learning higher-order sequential structure with cloned hidden Markov models
- Ross S., 2008, Advances in neural information processing systems, 20
- 10.1371/journal.pcbi.1005768 · DOI · Paper page
- Ryan R., 1985, Intrinsic motivation and self-determination in human behavior
- 10.1109/IJCNN.1991.170605 · DOI · Paper page
- 10.1080/09540090600768658 · DOI · Paper page
- Schrittwieser J., 2019, Mastering Atari, go, chess and shogi by planning with a learned model
- 10.3389/fpsyg.2013.00710 · DOI · Paper page
- 10.7554/eLife.41703 · DOI · Paper page
- Sengupta, B. & Friston, K. (2018). How robust are deep neural networks? arXiv:1804.11313. · arXiv
- 10.1073/pnas.1505483112 · DOI · Paper page
- 10.1103/PhysRevLett.109.120604 · DOI · Paper page
- 10.1109/IJCNN.2016.7727309 · DOI · Paper page
- Sutton R. S., 1998, Reinforcement learning: An introduction
- Tishby N., 1999, Proceedings of the 37th Annual Allerton Conference on Communication, Control, and Computing, 368
- Tishby N., 2010, Perception-reason-action cycle: Models, algorithms and systems
- Tishby N., 2015, Deep learning and the information bottleneck principle
- Todorov E., 2008, Proceedings of the IEEE Conference on Decision and Control
- Toussaint M., 2006, Proceedings of the 23rd Int. Conf. on Machine Learning
- Tribus M., 1961, Thermodynamics and thermostatics: An introduction to energy, information and states of matter, with engineering applications
- Tschantz A., 2019, Scaling active inference
- van den Broek J. L., 2010, Uncertainty in Artificial Intelligence, 6, 1
- Von Neumann J., 1944, Theory of games and economic behavior
- Winn J., 2005, Journal of Machine Learning Research, 6, 661
- 10.1109/TIT.2005.850085 · DOI · Paper page
Cited by
Active inference on discrete state-spaces: A synthesis
Da Costa, L., Parr, T., Sajid, N., Veselic, S., Neacsu, V., & Friston, K. (2020) · Journal of Mathematical Psychology · doi:10.1016/j.jmp.2020.102447 · Cited by 226
Self-citationPredictive processing as a systematic basis for identifying the neural correlates of consciousness
Hohwy, J., & Seth, A. (2020) · Philosophy and the Mind Sciences · doi:10.33735/phimisci.2020.ii.64 · Cited by 170
The free energy principle made simpler but not too simple
Friston, K., Da Costa, L., Sajid, N., Heins, C., Ueltzhöffer, K., Pavliotis, G. A., & Parr, T. (2023) · Physics Reports · doi:10.1016/j.physrep.2023.07.001 · Cited by 163
“Please see [150, 148] for a treatment of things like empowerment [170], information bottleneck [171] and predictive information [172, 173].”
Self-citationNeural dynamics under active inference: plausibility and efficiency of information processing
Da Costa, L., Parr, T., Sengupta, B., & Friston, K. (2021) · Entropy · doi:10.3390/e23040454 · Cited by 38
Self-citationReward maximization through discrete active inference
Da Costa, L., Sajid, N., Parr, T., Friston, K., & Smith, R. (2023) · Neural Computation · doi:10.1162/neco_a_01574 · Cited by 35
Self-citation
Metadata
- Authors
- Friston, K., Da Costa, L., Hafner, D., Hesp, C., & Parr, T.
- Venue
- Neural Computation
- Publisher
- MIT Press - Journals
- 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
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.