Formula-E multi-car race strategy development—a novel approach using reinforcement learning

Simple item page
dc.contributor.authorLiu, Xuze
dc.contributor.authorFotouhi, Abbas
dc.contributor.authorAuger, Daniel
dc.date.accessioned2024-05-13T10:22:36Z
dc.date.available2024-05-13T10:22:36Z
dc.date.issued2024-05-07
dc.description.abstractElectric motorsport such as Formula E is becoming more and more popular in recent years. Race strategy in such races can be very complex involving resource management, e.g. energy and thermal management, but more importantly multi-car interactions which could be both collaborative and competitive. Reinforcement Learning has been implemented in the literature for such electric racing strategy development but only accounts for one single car. In this paper, we proposed a new architecture iRaXL to implement reinforcement learning for such complex strategy development featuring hybrid action space, multi-car interactions, and non-zero-sum gaming. The iRaXL proves to be able to develop different strategies for individual competitors and also team-based objectives. In a bigger scope, this framework can be used to solve more generic problems with hybrid features such as zero/non-zero-sum games, discretized/continuous action space, and competition/collaboration interactions.en_UK
dc.identifier.citationLiu X, Fotouhi A, Auger D. (2024) Formula-E multi-car race strategy development—a novel approach using reinforcement learning. IEEE Transactions on Intelligent Transportation Systems. Available online 07 May 2024en_UK
dc.identifier.eissn1558-0016
dc.identifier.issn1524-9050
dc.identifier.urihttps://doi.org/10.1109/TITS.2024.3389155
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/21595
dc.language.isoen_UKen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectMotorsporten_UK
dc.subjectRace strategyen_UK
dc.subjectReinforcement learningen_UK
dc.subjectNeural networken_UK
dc.titleFormula-E multi-car race strategy development—a novel approach using reinforcement learningen_UK
dc.typeArticleen_UK
dcterms.dateAccepted2024-04-09

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Formula-E_multi-car-2024.pdf
Size:
3.73 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)