Hostname: page-component-f554764f5-qhdkw Total loading time: 0 Render date: 2025-04-22T02:18:16.614Z Has data issue: false hasContentIssue false
  • English
  • Français

Quo vadis, planning?

Published online by Cambridge University Press:  23 September 2024

Jacques Pesnot-Lerousseau  and
Christopher Summerfield Open the ORCID record for Christopher Summerfield [Opens in a new window]
Jacques Pesnot-Lerousseau
Affiliation:
Institute for Language, Communication, and the Brain, Aix-Marseille Univ, Marseille, France [email protected] Aix Marseille Univ, Inserm, INS, Inst Neurosci Syst, Marseille, France
Christopher Summerfield*
Affiliation:
Department of Experimental Psychology, University of Oxford, Oxford, UK [email protected] https://humaninformationprocessing.com/
*
*Corresponding author.
Get access Rights & Permissions [Opens in a new window]

Abstract

Deep meta-learning is the driving force behind advances in contemporary AI research, and a promising theory of flexible cognition in natural intelligence. We agree with Binz et al. that many supposedly “model-based” behaviours may be better explained by meta-learning than by classical models. We argue that this invites us to revisit our neural theories of problem solving and goal-directed planning.

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 47 , 2024 , e160
Check for updates
Copyright
Copyright © The Author(s), 2024. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Chan, S. C. Y., Dasgupta, I., Kim, J., Kumaran, D., Lampinen, A. K., & Hill, F. (2022a). Transformers generalize differently from information stored in context vs in weights. https://doi.org/10.48550/ARXIV.2210.05675CrossRefGoogle Scholar
Chan, S. C. Y., Santoro, A., Lampinen, A. K., Wang, J. X., Singh, A., Richemond, P. H., … Hill, F. (2022b). Data distributional properties drive emergent in-context learning in transformers. https://doi.org/10.48550/ARXIV.2205.05055CrossRefGoogle Scholar
Daw, N. D., & Dayan, P. (2014). The algorithmic anatomy of model-based evaluation. Philosophical Transactions of the Royal Society B, 369, 20130478. https://doi.org/10.1098/rstb.2013.0478CrossRefGoogle ScholarPubMed
de Waal, F. (2016). Are we smart enough to know how smart animals are? W. W. Norton & Company.Google Scholar
Ericsson, K. A., & Charness, N. (1994). Expert performance: Its structure and acquisition. American Psychologist, 49, 725–747. https://doi.org/10.1037/0003-066X.49.8.725CrossRefGoogle Scholar
Ruoss, A., Delétang, G., Medapati, S., Grau-Moya, J., Wenliang, L. K., Catt, E., … Genewein, T. (2024). Grandmaster-level chess without search.Google Scholar
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., … Hassabis, D. (2018). A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science, 362, 1140–1144. https://doi.org/10.1126/science.aar6404CrossRefGoogle ScholarPubMed
Summerfield, C. (2022). Natural general intelligence: How understanding the brain can help us build A1. Oxford University Press.CrossRefGoogle Scholar
Van Opheusden, B., Kuperwajs, I., Galbiati, G., Bnaya, Z., Li, Y., & Ma, W. J. (2023). Expertise increases planning depth in human gameplay. Nature, 618, 1000–1005. https://doi.org/10.1038/s41586-023-06124-2CrossRefGoogle ScholarPubMed
Wang, J. X., Kurth-Nelson, Z., Kumaran, D., Tirumala, D., Soyer, H., Leibo, J.Z., … Botvinick, M. (2018). Prefrontal cortex as a meta-reinforcement learning system. Nature Neuroscience, 21, 860–868. https://doi.org/10.1038/s41593-018-0147-8CrossRefGoogle ScholarPubMed