{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T04:21:42Z","timestamp":1747282902887,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031475078"},{"type":"electronic","value":"9783031475085"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-47508-5_7","type":"book-chapter","created":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T09:16:09Z","timestamp":1706692569000},"page":"79-94","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Reward-Guided Individualised Communication for\u00a0Deep Reinforcement Learning in\u00a0Multi-Agent Systems"],"prefix":"10.1007","author":[{"given":"Yi-Yu","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao-Jun","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,1]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Amato, C., Chowdhary, G., Geramifard, A., \u00dcre, N.K., Kochenderfer, M.J.: Decentralized control of partially observable Markov decision processes. In: 52nd IEEE Conference on Decision and Control, pp. 2398\u20132405. IEEE (2013)","DOI":"10.1109\/CDC.2013.6760239"},{"issue":"4","key":"7_CR2","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","volume":"27","author":"DS Bernstein","year":"2002","unstructured":"Bernstein, D.S., Givan, R., Immerman, N., Zilberstein, S.: The complexity of decentralized control of Markov decision processes. Math. Oper. Res. 27(4), 819\u2013840 (2002)","journal-title":"Math. Oper. Res."},{"key":"7_CR3","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.engappai.2018.01.011","volume":"70","author":"L B\u00fardalo","year":"2018","unstructured":"B\u00fardalo, L., Terrasa, A., Juli\u00e1n, V., Garc\u00eda-Fornes, A.: The information flow problem in multi-agent systems. Eng. Appl. Artif. Intell. 70, 130\u2013141 (2018)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Busoniu, L., Babuska, R., De\u00a0Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst., Man, Cybern. Part C (Appl. Rev.) 38(2), 156\u2013172 (2008)","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Bu\u015foniu, L., Babu\u0161ka, R., De\u00a0Schutter, B.: Multi-agent reinforcement learning: an overview. In: Innovations in Multi-agent Systems and Applications-1, pp. 183\u2013221 (2010)","DOI":"10.1007\/978-3-642-14435-6_7"},{"issue":"11","key":"7_CR6","doi-asserted-by":"publisher","first-page":"4948","DOI":"10.3390\/app11114948","volume":"11","author":"L Canese","year":"2021","unstructured":"Canese, L., Cardarilli, G.C., Di Nunzio, L., Fazzolari, R., Giardino, D., Re, M., Span\u00f2, S.: Multi-agent reinforcement learning: a review of challenges and applications. Appl. Sci. 11(11), 4948 (2021)","journal-title":"Appl. Sci."},{"key":"7_CR7","unstructured":"Das, A., Gervet, T., Romoff, J., Batra, D., Parikh, D., Rabbat, M., Pineau, J.: Tarmac: targeted multi-agent communication. In: International Conference on Machine Learning, pp. 1538\u20131546. PMLR (2019)"},{"key":"7_CR8","first-page":"22069","volume":"33","author":"Z Ding","year":"2020","unstructured":"Ding, Z., Huang, T., Lu, Z.: Learning individually inferred communication for multi-agent cooperation. Adv. Neural. Inf. Process. Syst. 33, 22069\u201322079 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"7_CR9","unstructured":"Foerster, J., Assael, I.A., De\u00a0Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"7_CR10","unstructured":"Hoshen, Y.: Vain: attentional multi-agent predictive modeling. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"7_CR11","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"7_CR12","unstructured":"Lecun, Y., Bengio, Y.: Convolutional Networks for Images, Speech and Time Series, pp. 255\u2013258. The MIT Press (1995)"},{"key":"7_CR13","unstructured":"Li, Y.: Deep reinforcement learning: an overview. arXiv:1701.07274 (2017)"},{"key":"7_CR14","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter\u00a0Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"7_CR15","unstructured":"Niu, Y., Paleja, R.R., Gombolay, M.C.: Multi-agent graph-attention communication and teaming. In: AAMAS, pp. 964\u2013973 (2021)"},{"key":"7_CR16","unstructured":"Omidshafiei, S., Pazis, J., Amato, C., How, J.P., Vian, J.: Deep decentralized multi-task multi-agent reinforcement learning under partial observability. In: International Conference on Machine Learning, pp. 2681\u20132690. PMLR (2017)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Oroojlooy, A., Hajinezhad, D.: A review of cooperative multi-agent deep reinforcement learning. Appl. Intell. 1\u201346 (2022)","DOI":"10.1007\/s10489-022-04105-y"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. Technical report, California Univ San Diego La Jolla Inst for Cognitive Science (1985)","DOI":"10.21236\/ADA164453"},{"key":"7_CR19","unstructured":"Shoham, Y., Powers, R., Grenager, T.: Multi-agent reinforcement learning: a critical survey. Technical report, Citeseer (2003)"},{"key":"7_CR20","unstructured":"Singh, A., Jain, T., Sukhbaatar, S.: Learning when to communicate at scale in multiagent cooperative and competitive tasks. arXiv:1812.09755 (2018)"},{"key":"7_CR21","unstructured":"Sukhbaatar, S., Fergus, R., et\u00a0al.: Learning multiagent communication with backpropagation. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"7_CR22","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (2018)"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"7_CR24","unstructured":"Wang, Y., Zhong, F., Xu, J., Wang, Y.: Tom2c: target-oriented multi-agent communication and cooperation with theory of mind. arXiv:2111.09189 (2021)"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, K., Yang, Z., Ba\u015far, T.: Multi-agent reinforcement learning: a selective overview of theories and algorithms. In: Handbook of Reinforcement Learning and Control, pp. 321\u2013384 (2021)","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"7_CR26","unstructured":"Zhu, C., Dastani, M., Wang, S.: A survey of multi-agent reinforcement learning with communication. arXiv:2203.08975 (2022)"}],"container-title":["Advances in Intelligent Systems and Computing","Advances in Computational Intelligence Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47508-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T09:17:21Z","timestamp":1706692641000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47508-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031475078","9783031475085"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47508-5_7","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"UKCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"UK Workshop on Computational Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Birmingham","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ukci2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.uk-ci.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}