Skip to main content
SpringerLink
Log in

Pruning Dominated Policies in Multiobjective Pareto Q-Learning

  • Conference paper
  • First Online:
Advances in Artificial Intelligence (CAEPIA 2018)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 11160))

Included in the following conference series:

Abstract

The solution for a Multi-Objetive Reinforcement Learning problem is a set of Pareto optimal policies. MPQ-learning is a recent algorithm that approximates the whole set of all Pareto-optimal deterministic policies by directly generalizing Q-learning to the multiobjective setting. In this paper we present a modification of MPQ-learning that avoids useless cyclical policies and thus improves the number of training steps required for convergence.

Supported by: the Spanish Government, Agencia Estatal de Investigación (AEI) and European Union, Fondo Europeo de Desarrollo Regional (FEDER), grant TIN2016-80774-R (AEI/FEDER, UE); and Plan Propio de Investigación de la Universidad de Málaga - Campus de Excelencia Internacional Andalucía Tech.

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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

References

  1. Drugan, M., Wiering, M., Vamplew, P., Chetty, M.: Editorial: special issue on multi-objective reinforcement learning. Neurocomputing 263, 1–2 (2017)

    Article  Google Scholar 

  2. Roijers, D.M., Vamplew, P., Whiteson, S., Dazeley, R.: A survey of multi-objective sequential decision-making. J. Artif. Intell. Res. (JAIR) 48, 67–113 (2013)

    Article  MathSciNet  Google Scholar 

  3. Ruiz-Montiel, M., Mandow, L., Perez-de-la Cruz, J.-L.: A temporal difference method for multi-objective reinforcement learning. Neurocomputing 263, 15–25 (2017)

    Article  Google Scholar 

  4. Vamplew, P., Dazeley, R., Berry, A., Issabekov, R., Dekker, E.: Empirical evaluation methods for multiobjective reinforcement learning algorithms. Mach. Learn. 84(1–2), 51–80 (2011)

    Article  MathSciNet  Google Scholar 

  5. Vamplew, P., Yearwood, J., Dazeley, R., Berry, A.: On the limitations of scalarisation for multi-objective reinforcement learning of Pareto fronts. In: Wobcke, W., Zhang, M. (eds.) AI 2008. LNCS (LNAI), vol. 5360, pp. 372–378. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-89378-3_37

    Chapter  Google Scholar 

  6. Van Moffaert, K., Nowé, A.: Multi-objective reinforcement learning using sets of Pareto dominating policies. J. Mach. Learn. Res. 15, 3663–3692 (2014)

    MathSciNet  MATH  Google Scholar 

  7. Wiering, M.A., Withagen, M., Drugan, M.M.: Model-based multi-objective reinforcement learning. In: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) (2014)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Andalucía Tech, Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, Málaga, Spain

    Lawrence Mandow & José-Luis Pérez-de-la-Cruz

Authors
  1. Lawrence Mandow
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. José-Luis Pérez-de-la-Cruz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lawrence Mandow .

Editor information

Editors and Affiliations

  1. Andalusian Research Institute on Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, Spain

    Francisco Herrera

  2. Andalusian Research Institute on Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, Spain

    Sergio Damas

  3. Andalusian Research Institute on Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, Spain

    Rosana Montes

  4. Andalusian Research Institute on Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, Spain

    Sergio Alonso

  5. Andalusian Research Institute on Data Science and Computational Intelligence (DaSCI), University of Granada, Granada, Spain

    Óscar Cordón

  6. Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain

    Antonio González

  7. School of Engineering, Pablo de Olavide University, Seville, Spain

    Alicia Troncoso

Rights and permissions

Reprints and permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Mandow, L., Pérez-de-la-Cruz, JL. (2018). Pruning Dominated Policies in Multiobjective Pareto Q-Learning. In: Herrera, F., et al. Advances in Artificial Intelligence. CAEPIA 2018. Lecture Notes in Computer Science(), vol 11160. Springer, Cham. https://doi.org/10.1007/978-3-030-00374-6_23

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-00374-6_23

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-00373-9

  • Online ISBN: 978-3-030-00374-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation