Formula-E race strategy development using distributed policy gradient reinforcement learning

Simple item page
dc.contributor.authorLiu, Xuze
dc.contributor.authorFotouhi, Abbas
dc.contributor.authorAuger, Daniel J.
dc.date.accessioned2021-01-25T17:57:04Z
dc.date.available2021-01-25T17:57:04Z
dc.date.issued2021-01-20
dc.description.abstractEnergy and thermal management is a crucial element in Formula-E race strategy development. In this study, the race-level strategy development is formulated into a Markov decision process (MDP) problem featuring a hybrid-type action space. Deep Deterministic Policy Gradient (DDPG) reinforcement learning is implemented under distributed architecture Ape-X and integrated with the prioritized experience replay and reward shaping techniques to optimize a hybrid-type set of actions of both continuous and discrete components. Soft boundary violation penalties in reward shaping, significantly improves the performance of DDPG and makes it capable of generating faster race finishing solutions. The new proposed method has shown superior performance in comparison to the Monte Carlo Tree Search (MCTS) with policy gradient reinforcement learning, which solves this problem in a fully discrete action space as presented in the literature. The advantages are faster race finishing time and better handling of ambient temperature rise.en_UK
dc.identifier.citationLiu X, Fotouhi A, Auger DJ. (2021) Formula-E race strategy development using distributed policy gradient reinforcement learning. Knowledge-Based Systems, Volume 216, March 2021, Article number 106781en_UK
dc.identifier.issn0950-7051
dc.identifier.urihttps://doi.org/10.1016/j.knosys.2021.106781
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/16246
dc.language.isoenen_UK
dc.publisherElsevieren_UK
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectEnergy managementen_UK
dc.subjectFormula-E race strategyen_UK
dc.subjectDeep deterministic policy gradienten_UK
dc.subjectReinforcement leaningen_UK
dc.titleFormula-E race strategy development using distributed policy gradient reinforcement learningen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Formula-E_race_strategy_development-2021.pdf
Size:
2.75 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)