dc.contributor.author | Espinós Longa, Marc | |
dc.contributor.author | Tsourdos, Antonios | |
dc.contributor.author | Inalhan, Gokhan | |
dc.date.accessioned | 2022-09-22T11:16:49Z | |
dc.date.available | 2022-09-22T11:16:49Z | |
dc.date.issued | 2022-09-05 | |
dc.identifier.citation | Espinós 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. 761-766 | en_UK |
dc.identifier.isbn | 978-1-6654-9480-9 | |
dc.identifier.issn | 0743-1619 | |
dc.identifier.uri | https://doi.org/10.23919/ACC53348.2022.9867171 | |
dc.identifier.uri | https://dspace.lib.cranfield.ac.uk/handle/1826/18463 | |
dc.description.abstract | Reinforcement 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.sponsorship | Engineering and Physical Sciences Research Council (EPSRC): 2454254. BAE Systems | en_UK |
dc.language.iso | en | en_UK |
dc.publisher | IEEE | en_UK |
dc.rights | Attribution-NonCommercial 4.0 International | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc/4.0/ | * |
dc.subject | Learning systems | en_UK |
dc.subject | Q-learning | en_UK |
dc.subject | Heuristic algorithms | en_UK |
dc.subject | Computational modeling | en_UK |
dc.subject | Scalability | en_UK |
dc.subject | Games | en_UK |
dc.subject | Predictive models | en_UK |
dc.title | Swarm intelligence in cooperative environments: N-step dynamic tree search algorithm extended analysis | en_UK |
dc.type | Conference paper | en_UK |
dc.identifier.eisbn | 978-1-6654-5196-3 |
The following license files are associated with this item: