Salvato in:
Dettagli Bibliografici
Autori principali: Vaartjes, Nathan, Francois-Lavet, Vincent
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2507.00011
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918076635676672
author Vaartjes, Nathan
Francois-Lavet, Vincent
author_facet Vaartjes, Nathan
Francois-Lavet, Vincent
contents Efficient elevator traffic management in large buildings is critical for minimizing passenger travel times and energy consumption. Because heuristic- or pattern-detection-based controllers struggle with the stochastic and combinatorial nature of dispatching, we model the six-elevator, fifteen-floor system at Vrije Universiteit Amsterdam as a Markov Decision Process and train an end-to-end Reinforcement Learning (RL) Elevator Group Control System (EGCS). Key innovations include a novel action space encoding to handle the combinatorial complexity of elevator dispatching, the introduction of infra-steps to model continuous passenger arrivals, and a tailored reward signal to improve learning efficiency. In addition, we explore various ways to adapt the discounting factor to the infra-step formulation. We investigate RL architectures based on Dueling Double Deep Q-learning, showing that the proposed RL-based EGCS adapts to fluctuating traffic patterns, learns from a highly stochastic environment, and thereby outperforms a traditional rule-based algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00011
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Novel RL approach for efficient Elevator Group Control Systems
Vaartjes, Nathan
Francois-Lavet, Vincent
Machine Learning
Artificial Intelligence
Efficient elevator traffic management in large buildings is critical for minimizing passenger travel times and energy consumption. Because heuristic- or pattern-detection-based controllers struggle with the stochastic and combinatorial nature of dispatching, we model the six-elevator, fifteen-floor system at Vrije Universiteit Amsterdam as a Markov Decision Process and train an end-to-end Reinforcement Learning (RL) Elevator Group Control System (EGCS). Key innovations include a novel action space encoding to handle the combinatorial complexity of elevator dispatching, the introduction of infra-steps to model continuous passenger arrivals, and a tailored reward signal to improve learning efficiency. In addition, we explore various ways to adapt the discounting factor to the infra-step formulation. We investigate RL architectures based on Dueling Double Deep Q-learning, showing that the proposed RL-based EGCS adapts to fluctuating traffic patterns, learns from a highly stochastic environment, and thereby outperforms a traditional rule-based algorithm.
title Novel RL approach for efficient Elevator Group Control Systems
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2507.00011