Publications

• Sorted by Date • Classified by Publication Type • Classified by Research Category •

Model-Based Reinforcement Learning with State Abstraction: A Survey

Rolf A. N. Starre, Marco Loog, and Frans A. Oliehoek. Model-Based Reinforcement Learning with State Abstraction: A Survey. In Proceedings of the 34th Benelux Conference on Artificial Intelligence (BNAIC) and the 30th Belgian Dutch Conference on Machine Learning (Benelearn), pp. 73–89, Springer International Publishing, 2023.

Download

pdf [352.8kB]  ps.gz ps HTML 

Abstract

Model-based reinforcement learning methods are promising since they can increase sample efficiency while simultaneously improving generalizability. Learning can also be made more efficient through state abstraction, which delivers more compact models. Model-based reinforcement learning methods have been combined with learning abstract models to profit from both effects. We consider a wide range of state abstractions that have been covered in the literature, from straightforward state aggregation to deep learned representations, and sketch challenges that arise when combining model-based reinforcement learning with abstraction. We further show how various methods deal with these challenges and point to open questions and opportunities for further research.

BibTeX Entry

@inproceedings{Starre23BNAICBenelearn_pp,
    author = {Starre, Rolf A. N. and Loog, Marco and Oliehoek, Frans A.},
    title =     {Model-Based Reinforcement Learning with State Abstraction: A Survey},
    booktitle = BNAICBenelearn22,
    year =      2023,
    note =      {},
    month =     {},
    publisher=  {Springer International Publishing},
    pages=      {73--89},
    doi =       {},
    keywords =   {refereed},
    abstract =  {
        Model-based reinforcement learning methods are promising since they can
        increase sample efficiency while simultaneously improving
        generalizability. Learning can also be made more efficient through
        state abstraction, which delivers more compact models. Model-based
        reinforcement learning methods have been combined with learning
        abstract models to profit from both effects. We consider a wide range
        of state abstractions that have been covered in the literature, from
        straightforward state aggregation to deep learned representations, and
        sketch challenges that arise when combining model-based reinforcement
        learning with abstraction. We further show how various methods deal
        with these challenges and point to open questions and opportunities for
        further research.
    }
}

Generated by bib2html.pl (written by Patrick Riley) on Tue Nov 05, 2024 16:13:37 UTC