Publications

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

A Cross-Field Review of State Abstraction for Markov Decision Processes

Elena Congeduti and Frans A. Oliehoek. A Cross-Field Review of State Abstraction for Markov Decision Processes. In Proceedings of the 34th Benelux Conference on Artificial Intelligence (BNAIC) and the 30th Belgian Dutch Conference on Machine Learning (Benelearn), November 2022.

Download

pdf [437.1kB]  

Abstract

Complex real-world systems pose a significant challenge to decision making: an agent needs to explore a large environment, deal with incomplete or noisy information, generalize the experience and learn from feedback to act optimally. These processes demand vast representation capacity, thus putting a burden on the agent’s limited computational and storage resources. State abstraction enables effective solutions by forming concise representations of the agents world. As such, it has been widely investigated by several research communities which have produced a variety of different approaches. Nonetheless, relations among them still remain unseen or roughly defined. This hampers potential applications of solution methods whose scope remains limited to the specific abstraction context for which they have been designed. To this end, the goal of this paper is to organize the developed approaches and identify connections between abstraction schemes as a fundamental step towards methods generalization. As a second contribution we discuss general abstraction properties with the aim of supporting a unified perspective for state abstraction.

BibTeX Entry

@inproceedings{Congeduti22BNAICBenelearn,
    author = {Congeduti, Elena and Oliehoek, Frans A.},
    title =     {A Cross-Field Review of State Abstraction for Markov Decision Processes},
    booktitle = BNAICBenelearn22,
    year =      2022,
    month =     nov,
    keywords =   {refereed},
    abstract =  {Complex real-world systems pose a significant challenge to decision making: an agent needs to explore a large environment, deal with incomplete or noisy information, generalize the experience and learn from feedback to act optimally. These processes demand vast representation capacity, thus putting a burden on the agent’s limited computational and storage resources. State abstraction enables effective solutions by forming concise representations of the agents world. As such, it has been widely investigated by several research communities which have produced a variety of different approaches. Nonetheless, relations among them still remain unseen or roughly defined. This hampers potential applications of solution methods whose scope remains limited to the specific abstraction context for which they have been designed. To this end, the goal of this paper is to organize the developed approaches and identify connections between abstraction schemes as a fundamental step towards methods generalization. As a second contribution we discuss general abstraction properties with the aim of supporting a unified perspective for state abstraction.
  }
}

Generated by bib2html.pl (written by Patrick Riley) on Mon Apr 08, 2024 20:28:07 UTC