Skip to main content
SpringerLink
Log in

Reinforcement Symbolic Learning

  • Conference paper
  • First Online:
Artificial Neural Networks and Machine Learning – ICANN 2021 (ICANN 2021)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 12894))

Included in the following conference series:

  • 2113 Accesses

Abstract

Complex problem solving involves representing structured knowledge, reasoning and learning, all at once. In this prospective study, we make explicit how a reinforcement learning paradigm can be applied to a symbolic representation of a concrete problem-solving task, modeled here by an ontology. This preliminary paper is only a set of ideas while feasibility verification is still a perspective of this work.

Supported by Inria, AEx AIDE https://team.inria.fr/mnemosyne/en/aide.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
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.

    Concretely the ontology role is to help specifying the representation of the world as conceived by the learner, i.e., what is observed and what is to be inferred during the learning activity, to solve the task. This also helps to verify the specification coherence of the model, which allows us to infer some assumptions about non observable elements of the learning process, as detailed in the supplementary material accessible here https://gitlab.inria.fr/line/aide-group/creacog

  2. 2.

    See here for a video illustration.

  3. 3.

    In the sense of https://json-schema.org.

  4. 4.

    We consider edit operations given an input (l+) adding, (l-) deleting or (l#) changing a value in a list, (t+) defining, (t-) undefining or (t#) changing a value in a tuple, each of these operations having a user-defined positive cost, related to the literal extended semi-distances. The key point is that we consider restricted edit distances preserving the tree filiation, computable in polynomial time [7], which would not have been the case otherwise, or if considering the tree as a general graph or ontology portion.

  5. 5.

    In the sense of RDF and OWL2.

References

  1. Alexandre, F.: A global framework for a systemic view of brain modeling. Brain Inf. 8(1), 3 (2021)

    Google Scholar 

  2. Domenech, P., Koechlin, E.: Executive control and decision-making in the prefrontal cortex. Curr. Opin. Behav. Sci. 1, 101–106 (2015)

    Article  Google Scholar 

  3. Garnelo, M., Arulkumaran, K., Shanahan, M.: Towards deep symbolic reinforcement learning. arXiv:1609.05518 [cs] (Oct 2016), arXiv: 1609.05518

  4. Ma, Z., et al.: Interpretable reinforcement learning with neural symbolic logic. In: ICLR 2021: 9th International Conference on Learning Representations (2020)

    Google Scholar 

  5. Mercier, C., Chateau-Laurent, H., Alexandre, F., Viéville, T.: Ontology as neuronal-space manifold: towards symbolic and numerical artificial embedding. In: KRHCAI 2021 Workshop @ KR 2021: 18th International Conference on Principles of Knowledge Representation and Reasoning, Hanoi, Vietnam and/or Online, submitted (2021)

    Google Scholar 

  6. Mercier, C., Roux, L., Romero, M., Alexandre, F., Viéville, T.: Formalizing problem-solving in computational thinking : an ontology approach. In: ICDL 2021: IEEE International Conference on Development and Learning, Beijing, China (2021)

    Google Scholar 

  7. Ouangraoua, A., Ferraro, P.: A constrained edit distance algorithm between semi-ordered trees. Theor. Comput. Sci. 410(8–10), 837–846. Elsevier (2009)

    Google Scholar 

  8. Rmus, M., McDougle, S.D., Collins, A.G.: The role of executive function in shaping reinforcement learning. Curr. Opin. Behav. Sci. 38, 66–73 (2021)

    Article  Google Scholar 

  9. Singh, S., Lewis, R.L., Barto, A.G., Sorg, J.: Intrinsically motivated reinforcement learning: an evolutionary perspective. IEEE Trans. Auton. Mental Dev. 2(2), 70–82 (2010)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Mnemosyne Team, Inria Bordeaux, LaBRI and IMN, Bordeaux, France

    Chloé Mercier, Frédéric Alexandre & Thierry Viéville

Authors
  1. Chloé Mercier
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Frédéric Alexandre
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Thierry Viéville
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Chloé Mercier , Frédéric Alexandre or Thierry Viéville .

Editor information

Editors and Affiliations

  1. Comenius University in Bratislava, Bratislava, Slovakia

    Igor Farkaš

  2. iMotions A/S, Copenhagen, Denmark

    Paolo Masulli

  3. University of Tübingen, Tübingen, Baden-Württemberg, Germany

    Sebastian Otte

  4. Universität Hamburg, Hamburg, Germany

    Stefan Wermter

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Mercier, C., Alexandre, F., Viéville, T. (2021). Reinforcement Symbolic Learning. In: Farkaš, I., Masulli, P., Otte, S., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2021. ICANN 2021. Lecture Notes in Computer Science(), vol 12894. Springer, Cham. https://doi.org/10.1007/978-3-030-86380-7_49

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-86380-7_49

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-86379-1

  • Online ISBN: 978-3-030-86380-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation