IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0006421.html
   My bibliography  Save this article

Reinforcement Learning or Active Inference?

Author

Listed:
  • Karl J Friston
  • Jean Daunizeau
  • Stefan J Kiebel

Abstract

This paper questions the need for reinforcement learning or control theory when optimising behaviour. We show that it is fairly simple to teach an agent complicated and adaptive behaviours using a free-energy formulation of perception. In this formulation, agents adjust their internal states and sampling of the environment to minimize their free-energy. Such agents learn causal structure in the environment and sample it in an adaptive and self-supervised fashion. This results in behavioural policies that reproduce those optimised by reinforcement learning and dynamic programming. Critically, we do not need to invoke the notion of reward, value or utility. We illustrate these points by solving a benchmark problem in dynamic programming; namely the mountain-car problem, using active perception or inference under the free-energy principle. The ensuing proof-of-concept may be important because the free-energy formulation furnishes a unified account of both action and perception and may speak to a reappraisal of the role of dopamine in the brain.

Suggested Citation

  • Karl J Friston & Jean Daunizeau & Stefan J Kiebel, 2009. "Reinforcement Learning or Active Inference?," PLOS ONE, Public Library of Science, vol. 4(7), pages 1-13, July.
  • Handle: RePEc:plo:pone00:0006421
    DOI: 10.1371/journal.pone.0006421
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0006421
    Download Restriction: no

    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0006421&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pone.0006421?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Colin Camerer, 2003. "Behavioural studies of strategic thinking," Levine's Bibliography 506439000000000490, UCLA Department of Economics.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Alexander Tschantz & Anil K Seth & Christopher L Buckley, 2020. "Learning action-oriented models through active inference," PLOS Computational Biology, Public Library of Science, vol. 16(4), pages 1-30, April.
    2. Jaroslav Vítků & Petr Dluhoš & Joseph Davidson & Matěj Nikl & Simon Andersson & Přemysl Paška & Jan Šinkora & Petr Hlubuček & Martin Stránský & Martin Hyben & Martin Poliak & Jan Feyereisl & Marek Ros, 2020. "ToyArchitecture: Unsupervised learning of interpretable models of the environment," PLOS ONE, Public Library of Science, vol. 15(5), pages 1-50, May.
    3. Francesco Donnarumma & Domenico Maisto & Giovanni Pezzulo, 2016. "Problem Solving as Probabilistic Inference with Subgoaling: Explaining Human Successes and Pitfalls in the Tower of Hanoi," PLOS Computational Biology, Public Library of Science, vol. 12(4), pages 1-30, April.
    4. Jennifer A. Loughmiller-Cardinal & James Scott Cardinal, 2023. "The Behavior of Information: A Reconsideration of Social Norms," Societies, MDPI, vol. 13(5), pages 1-27, April.
    5. Gianluigi Mongillo & Hanan Shteingart & Yonatan Loewenstein, 2014. "The Misbehavior of Reinforcement Learning," Discussion Paper Series dp661, The Federmann Center for the Study of Rationality, the Hebrew University, Jerusalem.
    6. Mateus Joffily & Giorgio Coricelli, 2013. "Emotional valence and the free-energy principle," Post-Print halshs-00862392, HAL.
    7. Stefano Palminteri & Germain Lefebvre & Emma J Kilford & Sarah-Jayne Blakemore, 2017. "Confirmation bias in human reinforcement learning: Evidence from counterfactual feedback processing," PLOS Computational Biology, Public Library of Science, vol. 13(8), pages 1-22, August.
    8. Dongqi Han & Kenji Doya & Dongsheng Li & Jun Tani, 2024. "Synergizing habits and goals with variational Bayes," Nature Communications, Nature, vol. 15(1), pages 1-14, December.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. David Macro & Jeroen Weesie, 2016. "Inequalities between Others Do Matter: Evidence from Multiplayer Dictator Games," Games, MDPI, vol. 7(2), pages 1-23, April.
    2. Yongjun Tang & Qi Li & Fen Zhou & Mingjia Sun, 2024. "Does Clan Culture Promote Corporate Natural Resource Disclosure? Evidence from Chinese Natural Resource-Based Listed Companies," Journal of Business Ethics, Springer, vol. 192(1), pages 167-190, June.
    3. Giorgia Ponsi & Maria Serena Panasiti & Salvatore Maria Aglioti & Marco Tullio Liuzza, 2017. "Right-wing authoritarianism and stereotype-driven expectations interact in shaping intergroup trust in one-shot vs multiple-round social interactions," PLOS ONE, Public Library of Science, vol. 12(12), pages 1-23, December.
    4. Hans-Rüdiger Pfister & Gisela Böhm, 2012. "Responder Feelings in a Three-Player Three-Option Ultimatum Game: Affective Determinants of Rejection Behavior," Games, MDPI, vol. 3(1), pages 1-29, February.
    5. Nagel, Rosemarie & Bühren, Christoph & Frank, Björn, 2017. "Inspired and inspiring: Hervé Moulin and the discovery of the beauty contest game," Mathematical Social Sciences, Elsevier, vol. 90(C), pages 191-207.
    6. Pennings, Clint L.P. & van Dalen, Jan & Rook, Laurens, 2019. "Coordinating judgmental forecasting: Coping with intentional biases," Omega, Elsevier, vol. 87(C), pages 46-56.
    7. Shanshan Zhen & Rongjun Yu, 2016. "Tend to Compare and Tend to Be Fair: The Relationship between Social Comparison Sensitivity and Justice Sensitivity," PLOS ONE, Public Library of Science, vol. 11(5), pages 1-17, May.
    8. Iris Vilares & Gregory Dam & Konrad Kording, 2011. "Trust and Reciprocity: Are Effort and Money Equivalent?," PLOS ONE, Public Library of Science, vol. 6(2), pages 1-9, February.
    9. Wako Yoshida & Ray J Dolan & Karl J Friston, 2008. "Game Theory of Mind," PLOS Computational Biology, Public Library of Science, vol. 4(12), pages 1-14, December.
    10. Ramzi Mabsout, 2018. "The Backward Induction Controversy as a Metaphorical Problem," Economic Thought, World Economics Association, vol. 7(1), pages 24-49, March.
    11. Paraskevas Lekeas & Giorgos Stamatopoulos, 2014. "Cooperative oligopoly games with boundedly rational firms," Annals of Operations Research, Springer, vol. 223(1), pages 255-272, December.
    12. Nir Halevy, 2020. "Strategic thinking and behavior during a pandemic," Judgment and Decision Making, Society for Judgment and Decision Making, vol. 15(5), pages 648-659, September.
    13. Andrea Morone & Serena Sandri & Tobias Uske, 2006. "On the absorbability of the Guessing Game Theory - A Theoretical and Experimental Analysis," Papers on Strategic Interaction 2006-33, Max Planck Institute of Economics, Strategic Interaction Group.
    14. Horton, Joanne & Krishna Kumar, Dhanya & Wood, Anthony, 2020. "Detecting academic fraud using Benford law: The case of Professor James Hunton," Research Policy, Elsevier, vol. 49(8).
    15. Danková, Katarína & Servátka, Maroš, 2015. "The house money effect and negative reciprocity," Journal of Economic Psychology, Elsevier, vol. 48(C), pages 60-71.
    16. Jordan, Matthew R. & Dickens, William T. & Hauser, Oliver P. & Rand, David G., 2022. "The role of inequity aversion in microloan defaults," Behavioural Public Policy, Cambridge University Press, vol. 6(2), pages 303-324, April.
    17. Kirgios, Erika L. & Chang, Edward H. & Milkman, Katherine L., 2020. "Going it alone: Competition increases the attractiveness of minority status," Organizational Behavior and Human Decision Processes, Elsevier, vol. 161(C), pages 20-33.
    18. A. B. Leoneti & G. A. Prataviera, 2020. "Entropy-Norm space for geometric selection of strict Nash equilibria in n-person games," Papers 2003.09225, arXiv.org.
    19. Tsuyoshi Hatori & Hayeong Jeong & Kiyoshi Kobayashi, 2014. "Regional learning and trust formation," Chapters, in: Charlie Karlsson & Börje Johansson & Kiyoshi Kobayashi & Roger R. Stough (ed.), Knowledge, Innovation and Space, chapter 8, pages 180-212, Edward Elgar Publishing.
    20. Conrads, Julian & Irlenbusch, Bernd, 2011. "Strategic Ignorance in Bargaining," IZA Discussion Papers 6087, Institute of Labor Economics (IZA).

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0006421. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.