Publication:
Emergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian models

Simple item page
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Planificación y Aprendizajees
dc.contributor.authorMartínez Gil, Francisco
dc.contributor.authorLozano, Miguel
dc.contributor.authorFernández Rebollo, Fernando
dc.contributor.funderMinisterio de Economía y Competitividad (España)es
dc.date.accessioned2020-01-15T16:45:38Z
dc.date.available2020-01-15T16:45:38Z
dc.date.issued2017-05-01
dc.description.abstractThis paper analyzes the emergent behaviors of pedestrian groups that learn through the multiagent reinforcement learning model developed in our group. Five scenarios studied in the pedestrian model literature, and with different levels of complexity, were simulated in order to analyze the robustness and the scalability of the model. Firstly, a reduced group of agents must learn by interaction with the environment in each scenario. In this phase, each agent learns its own kinematic controller, that will drive it at a simulation time. Secondly, the number of simulated agents is increased, in each scenario where agents have previously learnt, to test the appearance of emergent macroscopic behaviors without additional learning. This strategy allows us to evaluate the robustness and the consistency and quality of the learned behaviors. For this purpose several tools from pedestrian dynamics, such as fundamental diagrams and density maps, are used. The results reveal that the developed model is capable of simulating human-like micro and macro pedestrian behaviors for the simulation scenarios studied, including those where the number of pedestrians has been scaled by one order of magnitude with respect to the situation learned.es
dc.description.sponsorshipThis work has been supported by grant TIN2015-65686-C5-1-R of Ministerio de Economía y Competitividad.en
dc.identifier.bibliographicCitationF. Martínez, M. A. Lozano, F. Fernández. (2017). Emergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian models. Simulation Modelling Practice and Theory, 74, pp. 117-133en
dc.identifier.doihttps://doi.org/10.1016/j.simpat.2017.03.003
dc.identifier.issn1569-190X
dc.identifier.publicationfirstpage117
dc.identifier.publicationlastpage133
dc.identifier.publicationtitleSimulation Modelling Practice and theoryen
dc.identifier.publicationvolume74
dc.identifier.urihttps://hdl.handle.net/10016/29470
dc.identifier.uxxiAR/0000020003
dc.language.isoenges
dc.publisherElsevieren
dc.relation.projectIDGobierno de España. TIN2015-65686-C5-1-Res
dc.rights© 2017 Elsevier B.V. All rights reserved.es
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España*
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subject.ecienciaInformáticaes
dc.subject.otherPedestrian simulation and modelingen
dc.subject.otherMulti-agent reinforcement learning (Marl)en
dc.subject.otherBehavioural simulationen
dc.subject.otherEmergent behavioursen
dc.titleEmergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian modelsen
dc.typeresearch article*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
emergent_SMPT_2017_ps.pdf
Size:
1.38 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
DI - PLG - Artículos de Revistas