Skip to main content

Maze Learning Using a Hyperdimensional Predictive Processing Cognitive Architecture

  • Conference paper
  • First Online:
Artificial General Intelligence (AGI 2022)

Abstract

We present the COGnitive Neural GENerative system (CogNGen), a cognitive architecture that combines two neurobiologically-plausible, computational models: predictive processing and hyperdimensional/vector-symbolic models. We draw inspiration from architectures such as ACT-R and Spaun/Nengo. CogNGen is in broad agreement with these, providing a level of detail between ACT-R’s high-level symbolic description of human cognition and Spaun’s low-level neurobiological description, furthermore creating the groundwork for designing agents that learn continually from diverse tasks and model human performance at larger scales than what is possible with current systems. We test CogNGen on four maze-learning tasks, including those that test memory and planning, and find that CogNGen matches performance of deep reinforcement learning models and exceeds on a task designed to test memory.

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

Access this chapter

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

Notes

  1. 1.

    Appendix: https://www.cs.rit.edu/~ago/cogngnen_agi2022_append.pdf.

References

  1. Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018)

  2. Chevalier-Boisvert, M., Willems, L., Pal, S.: Minimalistic gridworld environment for OpenAI gym. https://github.com/maximecb/gym-minigrid (2018)

  3. French, R.M.: Catastrophic forgetting in connectionist networks. Trends Cogn. Sci. 3(4), 128–135 (1999)

    Article  Google Scholar 

  4. Friston, K.: A theory of cortical responses. Philos. Trans. R. Soc. B: Biol. Sci. 360(1456), 815–836 (2005)

    Article  Google Scholar 

  5. Friston, K., FitzGerald, T., Rigoli, F., Schwartenbeck, P., Pezzulo, G.: Active inference: a process theory. Neural Comput. 29(1), 1–49 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  6. Hebb, D.O.: The Organization of Behavior: A Neuropsychological Theory (1949)

    Google Scholar 

  7. Hintzman, D.L.: MINERVA 2: a simulation model of human memory. Behav. Res. Methods Instrum. Comput. 16, 96–101 (1984). https://doi.org/10.3758/BF03202365

    Article  Google Scholar 

  8. Huang, S., Ontañón, S., Bamford, C., Grela, L.: Gym-\(\mu \)RTS: toward affordable full game real-time strategy games research with deep reinforcement learning. In: 2021 IEEE Conference on Games (CoG), pp. 1–8. IEEE (2021)

    Google Scholar 

  9. Kelly, M.A., Ghafurian, M., West, R.L., Reitter, D.: Indirect associations in learning semantic and syntactic lexical relationships. J. Mem. Lang. 115, 104153 (2020). https://doi.org/10.1016/j.jml.2020.104153

    Article  Google Scholar 

  10. Kelly, M.A., Mewhort, D.J.K., West, R.L.: The memory tesseract: Mathematical equivalence between composite and separate storage memory models. J. Math. Psychol. 77, 142–155 (2017)

    Article  MathSciNet  MATH  Google Scholar 

  11. Kruijne, W., Bohte, S.M., Roelfsema, P.R., Olivers, C.N.: Flexible working memory through selective gating and attentional tagging. Neur. Comput. 33(1), 1–40 (2021)

    Article  MathSciNet  MATH  Google Scholar 

  12. Mannering, W.M., Jones, M.N.: Catastrophic interference in predictive neural network models of distributional semantics. Comput. Brain Behav. 4(1), 18–33 (2021). https://doi.org/10.1007/s42113-020-00089-5

    Article  Google Scholar 

  13. McCloskey, M., Cohen, N.J.: Catastrophic interference in connectionist networks: the sequential learning problem. Psychol. Learn. Motiv. 24(109), 92 (1989)

    Google Scholar 

  14. Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)

    Article  Google Scholar 

  15. Ororbia, A.G., Kelly, M.A.: CogNGen: constructing the kernel of a hyperdimensional predictive processing cognitive architecture. In: Proceedings of the 44th Annual Conference of the Cognitive Science Society, pp. 1322–1329. Cognitive Science Society, Toronto, ON (2022). https://doi.org/10.31234/osf.io/g6hf4

  16. Ororbia, A., Kifer, D.: The neural coding framework for learning generative models. Nat. Commun. 13(1), 1–14 (2022)

    Article  Google Scholar 

  17. Ororbia, A., Mali, A.: Backprop-free reinforcement learning with active neural generative coding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36 (2022)

    Google Scholar 

  18. Rao, R.P., Ballard, D.H.: Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nat. Neurosci. 2(1), 79–87 (1999)

    Article  Google Scholar 

  19. Ritter, F.E., Tehranchi, F., Oury, J.D.: ACT-R: a cognitive architecture for modeling cognition. WIREs Cognit. Sci. 10(3), e1488 (2019)

    Article  Google Scholar 

  20. Schultz, W.: Reward functions of the basal ganglia. J. Neural Transm. 123(7), 679–693 (2016). https://doi.org/10.1007/s00702-016-1510-0

    Article  Google Scholar 

  21. Zhang, T., et al.: Bebold: exploration beyond the boundary of explored regions. arXiv preprint arXiv:2012.08621 (2020)

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Alexander G. Ororbia .

Editor information

Editors and Affiliations

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

Ororbia, A.G., Kelly, M.A. (2023). Maze Learning Using a Hyperdimensional Predictive Processing Cognitive Architecture. In: Goertzel, B., Iklé, M., Potapov, A., Ponomaryov, D. (eds) Artificial General Intelligence. AGI 2022. Lecture Notes in Computer Science(), vol 13539. Springer, Cham. https://doi.org/10.1007/978-3-031-19907-3_31

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19907-3_31

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19906-6

  • Online ISBN: 978-3-031-19907-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics