Object

Title: Utilization of Deep Reinforcement Learning for Discrete Resource Allocation Problem in Project Management – a Simulation Experiment

Title in english:

Wykorzystanie uczenia ze wzmocnieniem w problemach dyskretnej alokacji zasobów w zarządzaniu projektami – eksperyment symulacyjny

Creator:

Wójcik, Filip

Description:

Informatyka Ekonomiczna = Business Informatics, 2022, Nr 1 (63), s. 56-74

Abstrakt:

This paper tests the applicability of deep reinforcement learning (DRL) algorithms to simulated problems of constrained discrete and online resource allocation in project management. DRL is an extensively researched method in various domains, although no similar case study was found when writing this paper. The hypothesis was that a carefully tuned RL agent could outperform an optimisation-based solution. The RL agents: VPG, AC, and PPO, were compared against a classic constrained optimisation algorithm in trials: “easy”/”moderate”/”hard” (70/50/30% average project success rate). Each trial consisted of 500 independent, stochastic simulations. The significance of the differences was checked using a Welch ANOVA on significance level alpha = 0.01, followed by post hoc comparisons for false-discovery control. The experiment revealed that the PPO agent performed significantly better in moderate and hard simulations than the optimisation approach and other RL methods.

Publisher:

Publishing House of Wroclaw University of Economics and Business

Place of publication:

Wroclaw

Date:

2022

Resource Type:

artykuł

Resource Identifier:

doi:10.15611/ie.2022.1.05 ; oai:dbc.wroc.pl:120578

Language:

eng

Relation:

Informatyka Ekonomiczna = Business Informatics, 2022, Nr 1 (63)

Rights:

Pewne prawa zastrzeżone na rzecz Autorów i Wydawcy

Access Rights:

Dla wszystkich zgodnie z licencją

License:

CC BY-SA 4.0

Location:

Uniwersytet Ekonomiczny we Wrocławiu

Similar

×

Citation

Citation style:

This page uses 'cookies'. More information