Skip to main content
Springer Nature Link
Log in

ADAM: A Prototype of Hierarchical Neuro-Symbolic AGI

  • Conference paper
  • First Online:
Artificial General Intelligence (AGI 2023)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 13921))

Included in the following conference series:

  • 1189 Accesses

Abstract

Intelligent agents are characterized primarily by their far-sighted expedient behavior. We present a working prototype of an intelligent agent (ADAM) based on a novel hierarchical neuro-symbolic architecture (Deep Control) for deep reinforcement learning with a potentially unlimited planning horizon. The control parameters form a hierarchy of formal languages, where higher-level alphabets contain the semantic meanings of lower-level vocabularies.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 69.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 89.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Bakker, B., Schmidhuber, J., et al.: Hierarchical reinforcement learning based on subgoal discovery and subpolicy specialization. In: Proceedings of the 8-th Conference on Intelligent Autonomous Systems, pp. 438–445 (2004)

    Google Scholar 

  2. Barto, A.G., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Discret. Event Dyn. Syst. 13(1–2), 41–77 (2003)

    Article  MathSciNet  MATH  Google Scholar 

  3. Botvinick, M.M.: Hierarchical reinforcement learning and decision making. Curr. Opin. Neurobiol. 22(6), 956–962 (2012)

    Article  Google Scholar 

  4. Dietterich, T.G., et al.: The MAXQ method for hierarchical reinforcement learning. In: ICML, vol. 98, pp. 118–126 (1998)

    Google Scholar 

  5. Friston, K.J., Parr, T., Yufik, Y., Sajid, N., Price, C.J., Holmes, E.: Generative models, linguistic communication and active inference. Neurosci. Biobehav. Rev. 118, 42–64 (2020)

    Article  Google Scholar 

  6. Gage, P.: A new algorithm for data compression. C Users J. 12(2), 23–38 (1994)

    Google Scholar 

  7. Kotseruba, I., Tsotsos, J.K.: 40 years of cognitive architectures: core cognitive abilities and practical applications. Artif. Intell. Rev. 53(1), 17–94 (2020)

    Article  Google Scholar 

  8. Laird, J.E., Lebiere, C., Rosenbloom, P.S.: A standard model of the mind: toward a common computational framework across artificial intelligence, cognitive science, neuroscience, and robotics. AI Mag. 38(4), 13–26 (2017)

    Google Scholar 

  9. Langley, P., Laird, J.E., Rogers, S.: Cognitive architectures: research issues and challenges. Cogn. Syst. Res. 10(2), 141–160 (2009)

    Article  Google Scholar 

  10. Laukien, E., Crowder, R., Byrne, F.: Feynman machine: the universal dynamical systems computer (2016). arXiv preprint arXiv:1609.03971

  11. Levy, A., Platt, R., Saenko, K.: Hierarchical reinforcement learning with hindsight (2018). arXiv preprint arXiv:1805.08180

  12. Levy, O., Goldberg, Y.: Neural word embedding as implicit matrix factorization. In: Advances in Neural Information Processing Systems, pp. 2177–2185 (2014)

    Google Scholar 

  13. Nachum, O., Gu, S.S., Lee, H., Levine, S.: Data-efficient hierarchical reinforcement learning. Adv. Neural Inf. Process. Syst. 31, 3307–3317 (2018)

    Google Scholar 

  14. Pateria, S., Subagdja, B., Tan, A.H., Quek, C.: Hierarchical reinforcement learning: a comprehensive survey. ACM Comput. Surv. (CSUR) 54(5), 1–35 (2021)

    Google Scholar 

  15. Pezzulo, G., Parr, T., Friston, K.: The evolution of brain architectures for predictive coding and active inference. Philos. Trans. R. Soc. B 377(1844), 20200531 (2022)

    Article  Google Scholar 

  16. Pezzulo, G., Rigoli, F., Friston, K.J.: Hierarchical active inference: a theory of motivated control. Trends Cogn. Sci. 22(4), 294–306 (2018)

    Article  Google Scholar 

  17. Ritter, F.E., Tehranchi, F., Oury, J.D.: ACT-R: a cognitive architecture for modeling cognition. Wiley Interdiscip. Rev. Cogn. Sci. 10(3), e1488 (2019)

    Google Scholar 

  18. Russell, S.: Human compatible: artificial intelligence and the problem of control. Penguin (2019)

    Google Scholar 

  19. Shumskii, S.: ADAM: a model of artificial psyche. Autom. Remote Control 83(6), 847–856 (2022). https://doi.org/10.1134/S0005117922060030

    Article  MathSciNet  Google Scholar 

  20. Shumsky, S.: Machine Intelligence. Essays on the theory of machine learning and artificial intelligence. RIOR (2019). (in Russian). https://doi.org/10.29039/02011-1

  21. Shumsky, S.: Scalable natural language understanding: from scratch, on the fly. In: 2018 International Conference on Artificial Intelligence Applications and Innovations (IC-AIAI), pp. 73–74. IEEE (2018). https://doi.org/10.1109/IC-AIAI.2018.8674432

  22. Vezhnevets, A.S., et al.: Feudal networks for hierarchical reinforcement learning. In: International Conference on Machine Learning, pp. 3540–3549. PMLR (2017)

    Google Scholar 

  23. Wainwright, M.J.: Variance-reduced \( q \)-learning is minimax optimal (2019). arXiv preprint arXiv:1906.04697

  24. Wang, R., Yu, R., An, B., Rabinovich, Z.: I\(^{2}\)HRL: interactive influence-based hierarchical reinforcement learning. In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 3131–3138 (2021)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Moscow Institute of Physics and Technology, Dolgoprudny, 141701, Russian Federation

    Sergey Shumsky & Oleg Baskov

Authors
  1. Sergey Shumsky
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Oleg Baskov
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sergey Shumsky .

Editor information

Editors and Affiliations

  1. Department of Psychology, Stockholm University, Stockholm, Sweden

    Patrick Hammer

  2. Örebro University, Örebro, Sweden

    Marjan Alirezaie

  3. University of Gothenburg, Gothenburg, Sweden

    Claes Strannegård

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Shumsky, S., Baskov, O. (2023). ADAM: A Prototype of Hierarchical Neuro-Symbolic AGI. In: Hammer, P., Alirezaie, M., Strannegård, C. (eds) Artificial General Intelligence. AGI 2023. Lecture Notes in Computer Science(), vol 13921. Springer, Cham. https://doi.org/10.1007/978-3-031-33469-6_26

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-33469-6_26

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-33468-9

  • Online ISBN: 978-3-031-33469-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics