{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T06:10:59Z","timestamp":1760854259913,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030898984"},{"type":"electronic","value":"9783030898991"}],"license":[{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:00:00Z","timestamp":1634688000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-89899-1_20","type":"book-chapter","created":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T22:38:52Z","timestamp":1634683132000},"page":"197-206","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Mixed Cooperative-Competitive Communication Using Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Astrid","family":"Vanneste","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wesley","family":"Van Wijnsberghe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon","family":"Vanneste","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Mets","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siegfried","family":"Mercelis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven","family":"Latr\u00e9","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Hellinckx","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,10,20]]},"reference":[{"key":"20_CR1","unstructured":"Das, A., et al.: Tarmac: targeted multi-agent communication. arXiv preprint arXiv:1810.11187 (2018)"},{"key":"20_CR2","unstructured":"Ding, Z., Huang, T., Lu, Z.: Learning individually inferred communication for multi-agent cooperation. arXiv preprint arXiv:2006.06455 (2021)"},{"key":"20_CR3","unstructured":"Foerster, J., Assael, I.A., De\u00a0Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 2137\u20132145 (2016)"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Goldman, C.V., Zilberstein, S.: Optimizing information exchange in cooperative multi-agent systems. In: Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, pp. 137\u2013144 (2003)","DOI":"10.1145\/860575.860598"},{"key":"20_CR5","volume-title":"Dynamic Programming and Markov Processes","author":"RA Howard","year":"1960","unstructured":"Howard, R.A.: Dynamic Programming and Markov Processes. MIT Press, Cambridge (1960)"},{"key":"20_CR6","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 31, pp. 7254\u20137264. Curran Associates, Inc. (2018). http:\/\/papers.nips.cc\/paper\/7956-learning-attentional-communication-for-multi-agent-cooperation.pdf"},{"key":"20_CR7","unstructured":"Liang, E., et al.: RLlib: abstractions for distributed reinforcement learning. In: International Conference on Machine Learning (ICML) (2018)"},{"key":"20_CR8","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Neural Information Processing Systems (NIPS) (2017)"},{"key":"20_CR9","unstructured":"Mao, H., Gong, Z., Ni, Y., Xiao, Z.: Accnet: actor-coordinator-critic net for \u201clearning-to-communicate\u201d with deep multi-agent reinforcement learning. arXiv preprint arXiv:1706.03235 (2017)"},{"key":"20_CR10","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A., Veness, J., Bellemare, M., Graves, A., Riedmiller, M., Fidjeland, A., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518, 529\u201333 (2015). https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Mordatch, I., Abbeel, P.: Emergence of grounded compositional language in multi-agent populations. arXiv preprint arXiv:1703.04908 (2017)","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Oliehoek, F.A., Amato, C., et\u00a0al.: A concise introduction to decentralized POMDPs, vol.\u00a01. Springer (2016)","DOI":"10.1007\/978-3-319-28929-8_1"},{"key":"20_CR13","unstructured":"Peng, P., Wen, Y., Yang, Y., Yuan, Q., Tang, Z., Long, H., Wang, J.: Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games. arXiv preprint arXiv:1703.10069 (2017)"},{"key":"20_CR14","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C., Guez, A., Sifre, L., Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016). https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"20_CR15","unstructured":"Sukhbaatar, S., Fergus, R., et\u00a0al.: Learning multiagent communication with backpropagation. In: Advances in Neural Information Processing Systems, pp. 2244\u20132252 (2016)"},{"key":"20_CR16","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning based on team reward. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS \u201918, pp. 2085\u20132087. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC (2018)"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: Independent vs. cooperative agents. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 330\u2013337. Morgan Kaufmann (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"20_CR18","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1007\/978-3-030-33509-0_69","volume-title":"Advances on P2P, Parallel, Grid, Cloud and Internet Computing","author":"S Vanneste","year":"2020","unstructured":"Vanneste, S., Vanneste, A., Bosmans, S., Mercelis, S., Hellinckx, P.: Learning to communicate with multi-agent reinforcement learning using value-decomposition networks. In: Barolli, L., Hellinckx, P., Natwichai, J. (eds.) Advances on P2P, Parallel, Grid, Cloud and Internet Computing, pp. 736\u2013745. Springer, Cham (2020)"},{"key":"20_CR19","unstructured":"Vanneste, S., Vanneste, A., Mercelis, S., Hellinckx, P.: Learning to communicate using counterfactual reasoning. arXiv preprint arXiv:2006.07200 (2020)"}],"container-title":["Lecture Notes in Networks and Systems","Advances on P2P, Parallel, Grid, Cloud and Internet Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89899-1_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T22:32:17Z","timestamp":1673562737000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89899-1_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,20]]},"ISBN":["9783030898984","9783030898991"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89899-1_20","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2021,10,20]]},"assertion":[{"value":"20 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"3PGCIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on P2P, Parallel, Grid, Cloud and Internet Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fukuoka","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pgcic2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/voyager.ce.fit.ac.jp\/conf\/3pgcic\/2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}