Swarm intelligence in cooperative environments: N-step dynamic tree search algorithm extended analysis

Simple item page
dc.contributor.authorEspinós Longa, Marc
dc.contributor.authorTsourdos, Antonios
dc.contributor.authorInalhan, Gokhan
dc.date.accessioned2022-09-22T11:16:49Z
dc.date.available2022-09-22T11:16:49Z
dc.date.issued2022-09-05
dc.description.abstractReinforcement learning tree-based planning methods have been gaining popularity in the last few years due to their success in single-agent domains, where a perfect simulator model is available, e.g., Go and chess strategic board games. This paper pretends to extend tree search algorithms to the multi-agent setting in a decentralized structure, dealing with scalability issues and exponential growth of computational resources. The N-Step Dynamic Tree Search combines forward planning and direct temporal-difference updates, outperforming markedly state-of-the-art algorithms such as Q-Learning and SARSA. Future state transitions and rewards are predicted with a model built and learned from real interactions between agents and the environment. As an extension of previous work, this paper analyses the developed algorithm in the Hunter-Pursuit cooperative game against intelligent evaders. The N-Step Dynamic Tree Search aims to adapt the most successful single-agent learning methods to the multi-agent boundaries and demonstrates to be a remarkable advance compared to conventional temporal-difference techniques.en_UK
dc.description.sponsorshipEngineering and Physical Sciences Research Council (EPSRC): 2454254. BAE Systemsen_UK
dc.identifier.citationEspinós Longa M, Tsourdos A, Inalhan G. (2022) Swarm intelligence in cooperative environments: N-step dynamic tree search algorithm extended analysis. In: 2022 American Control Conference (ACC), 8-10 June 2022, Atlanta, GA, USA. pp. 761-766en_UK
dc.identifier.eisbn978-1-6654-5196-3
dc.identifier.isbn978-1-6654-9480-9
dc.identifier.issn0743-1619
dc.identifier.urihttps://doi.org/10.23919/ACC53348.2022.9867171
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/18463
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectLearning systemsen_UK
dc.subjectQ-learningen_UK
dc.subjectHeuristic algorithmsen_UK
dc.subjectComputational modelingen_UK
dc.subjectScalabilityen_UK
dc.subjectGamesen_UK
dc.subjectPredictive modelsen_UK
dc.titleSwarm intelligence in cooperative environments: N-step dynamic tree search algorithm extended analysisen_UK
dc.typeConference paperen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Swarm_intelligence_in_cooperative_environments-2022.pdf
Size:
2.91 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)