A Universal Approach to Feature Representation in Dynamic Task Assignment Problems

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

Dynamic task assignment concerns the optimal assignment of resources to tasks in a business process. Recently, Deep Reinforcement Learning (DRL) has been proposed as the state of the art for solving assignment problems. DRL methods usually employ a neural network (NN) as an approximator for the policy function, which ingests the state of the process and outputs a valuation of the possible assignments. However, representing the state and the possible assignments so that they can serve as inputs and outputs for a policy NN remains an open challenge, especially when tasks or resources have features with an infinite number of possible values. To solve this problem, this paper proposes a method for representing and solving assignment problems with infinite state and action spaces. In doing so, it provides three contributions: (I) A graph-based feature representation of assignment problems, which we call assignment graph; (II) A mapping from marked Colored Petri Nets to assignment graphs; (III) An adaptation of the Proximal Policy Optimization algorithm that can learn to solve assignment problems represented through assignment graphs. To evaluate the proposed representation method, we model three archetypal assignment problems ranging from finite to infinite state and action space dimensionalities. The experiments show that the method is suitable for representing and learning close-to-optimal task assignment policies regardless of the state and action space dimensionalities.
Originele taal-2Engels
TitelBusiness Process Management Forum: BPM 2024 Forum, Krakow, Poland, September 1-6, 2024, Proceedings
RedacteurenAndrea Marrella, Manuel Resinas, Mieke Jans, Michael Rosemann
Plaats van productieCham
UitgeverijSpringer
Pagina's197-213
Aantal pagina's17
ISBN van elektronische versie978-3-031-70418-5
ISBN van geprinte versie978-3-031-70417-8
DOI's
StatusGepubliceerd - 30 aug. 2024
Evenement22nd Business Process Management Conference 2024, BPM 2024 - Krakow, Polen
Duur: 1 sep. 20246 sep. 2024

Congres

Congres22nd Business Process Management Conference 2024, BPM 2024
Verkorte titelBPM 2024
Land/RegioPolen
StadKrakow
Periode1/09/246/09/24

Vingerafdruk

Duik in de onderzoeksthema's van 'A Universal Approach to Feature Representation in Dynamic Task Assignment Problems'. Samen vormen ze een unieke vingerafdruk.

Citeer dit