{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:27:10Z","timestamp":1743002830693,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789811934438"},{"type":"electronic","value":"9789811934445"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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\/978-981-19-3444-5_8","type":"book-chapter","created":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T09:05:06Z","timestamp":1658826306000},"page":"87-97","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Assured Multi-agent Reinforcement Learning with\u00a0Robust Agent-Interaction Adaptability"],"prefix":"10.1007","author":[{"given":"Joshua","family":"Riley","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radu","family":"Calinescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Colin","family":"Paterson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alec","family":"Banks","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,27]]},"reference":[{"key":"8_CR1","doi-asserted-by":"publisher","first-page":"28573","DOI":"10.1109\/ACCESS.2018.2831228","volume":"6","author":"A Dorri","year":"2018","unstructured":"Dorri, A., Kanhere, S.S., Jurdak, R.: Multi-agent systems: a survey. IEEE Access 6, 28573\u201328593 (2018)","journal-title":"IEEE Access"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Frasheri, M., C\u00fcr\u00fckl\u00fc, B., Esktr\u00f6m, M., Papadopoulos, A.V.: Adaptive autonomy in a search and rescue scenario. In: 2018 IEEE 12th International Conference on Self-adaptive and Self-organizing Systems (SASO), pp.\u00a0150\u2013155. IEEE (2018)","DOI":"10.1109\/SASO.2018.00026"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Hurtado, C., Ramirez, M.R., Alanis, A., Vazquez, S.O., Ramirez, B., Manrique, E.: Towards a multi-agent system for an informative healthcare mobile application. In: KES International Symposium on Agent and Multi-agent Systems: Technologies and Applications, pp.\u00a0215\u2013219. Springer (2018)","DOI":"10.1007\/978-3-319-92031-3_21"},{"key":"8_CR4","unstructured":"Abbas, H.A., Shaheen, S.I., Amin, M.H.: Organization of multi-agent systems: an overview. arXiv preprint arXiv:1506.09032 (2015)"},{"key":"8_CR5","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (2018)"},{"key":"8_CR6","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/978-3-642-14435-6_7","volume":"1","author":"L Bu\u015foniu","year":"2010","unstructured":"Bu\u015foniu, L., Babu\u0161ka, R., De Schutter, B.: Multi-agent reinforcement learning: an overview. Innov. Multi-agent Syst. Appl. 1, 183\u2013221 (2010)","journal-title":"Innov. Multi-agent Syst. Appl."},{"issue":"1","key":"8_CR7","first-page":"1437","volume":"16","author":"J Garc\u0131a","year":"2015","unstructured":"Garc\u0131a, J., Fern\u00e1ndez, F.: A comprehensive survey on safe reinforcement learning. J. Mach. Learn. Res. 16(1), 1437\u20131480 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, K., Yang, Z., Ba\u015far, T.: Multi-agent reinforcement learning: a selective overview of theories and algorithms. Handbook of Reinforcement Learning and Control, pp.\u00a0321\u2013384 (2021)","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Mason, G., Calinescu, R., Kudenko, D., Banks, A.: Assurance in reinforcement learning using quantitative verification. In: Advances in Hybridization of Intelligent Methods, pp.\u00a071\u201396. Springer (2018)","DOI":"10.1007\/978-3-319-66790-4_5"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Riley, J., Calinescu, R., Paterson, C., Kudenko, D., Banks, A.: Reinforcement learning with quantitative verification for assured multi-agent policies. In: 13th International Conference on Agents and Artificial Intelligence, York (2021)","DOI":"10.5220\/0010258102370245"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Riley, J., Calinescu, R., Paterson, C., Kudenko, D., Banks, A.: Utilising assured multi-agent reinforcement learning within safety-critical scenarios. Procedia Comput. Sci. 192, 1061\u20131070 (2021). Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 25th International Conference KES2021","DOI":"10.1016\/j.procs.2021.08.109"},{"key":"8_CR12","first-page":"22","volume":"21","author":"P Hernandez-Leal","year":"2018","unstructured":"Hernandez-Leal, P., Kartal, B., Taylor, M.E.: Is multiagent deep reinforcement learning the answer or the question? A brief survey. Learning 21, 22 (2018)","journal-title":"Learning"},{"key":"8_CR13","unstructured":"Faria, J.M.: Machine learning safety: an overview. In: Proceedings of the 26th Safety-Critical Systems Symposium, York, UK, pp.\u00a06\u20138 (2018)"},{"issue":"5","key":"8_CR14","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1007\/BF01211866","volume":"6","author":"H Hansson","year":"1994","unstructured":"Hansson, H., Jonsson, B.: A logic for reasoning about time and reliability. Formal Aspects Comput. 6(5), 512\u2013535 (1994)","journal-title":"Formal Aspects Comput."},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Kwiatkowska, M., Norman, G., Parker, D.: Prism 4.0: verification of probabilistic real-time systems. In: International Conference on Computer Aided Verification, pp.\u00a0585\u2013591. Springer (2011)","DOI":"10.1007\/978-3-642-22110-1_47"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Brunke, L., Greeff, M., Hall, A.W., Yuan, Z., Zhou, S., Panerati, J., Schoellig, A.P.: Safe learning in robotics: from learning-based control to safe reinforcement learning. arXiv preprint arXiv:2108.06266 (2021)","DOI":"10.1146\/annurev-control-042920-020211"},{"key":"8_CR17","unstructured":"Hasanbeig, M., Abate, A., Kroening, D.: Cautious reinforcement learning with logical constraints. arXiv preprint arXiv:2002.12156 (2020)"},{"key":"8_CR18","unstructured":"Huh, S., Yang, I.: Safe reinforcement learning for probabilistic reachability and safety specifications: a Lyapunov-based approach. arXiv preprint arXiv:2002.10126 (2020)"},{"key":"8_CR19","unstructured":"Wachi, A., Sui, Y.: Safe reinforcement learning in constrained Markov decision processes. In: International Conference on Machine Learning, pp.\u00a09797\u20139806. PMLR (2020)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Cheng, R., Orosz, G., Murray, R.M., Burdick, J.W.: End-to-end safe reinforcement learning through barrier functions for safety-critical continuous control tasks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 3387\u20133395 (2019)","DOI":"10.1609\/aaai.v33i01.33013387"},{"key":"8_CR21","unstructured":"Srinivasan, K., Eysenbach, B., Ha, S., Tan, J., Finn, C.: Learning to be safe: deep RL with a safety critic. arXiv preprint arXiv:2010.14603 (2020)"},{"key":"8_CR22","unstructured":"Jansen, N., K\u00f6nighofer, B., Junges, S., Serban, A., Bloem, R.: Safe reinforcement learning using probabilistic shields (2020)"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Mason, G.R., Calinescu, R.C., Kudenko, D., Banks, A.: Assured reinforcement learning with formally verified abstract policies. In: 9th International Conference on Agents and Artificial Intelligence (ICAART), York (2017)","DOI":"10.5220\/0006156001050117"},{"issue":"2","key":"8_CR24","doi-asserted-by":"publisher","first-page":"647","DOI":"10.2298\/CSIS191220009G","volume":"17","author":"Y Ge","year":"2020","unstructured":"Ge, Y., Zhu, F., Huang, W., Zhao, P., Liu, Q.: Multi-agent cooperation Q-learning algorithm based on constrained Markov game. Comput. Sci. Inf. Syst. 17(2), 647\u2013664 (2020)","journal-title":"Comput. Sci. Inf. Syst."},{"key":"8_CR25","unstructured":"Juliani, A., Berges, V.-P., Teng, E., Cohen, A., Harper, J., Elion, C., Goy, C., Gao, Y., Henry, H., Mattar, M., et\u00a0al.: Unity: a general platform for intelligent agents. arXiv preprint arXiv:1809.02627 (2018)"}],"container-title":["Smart Innovation, Systems and Technologies","Intelligent Decision Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-19-3444-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T09:10:46Z","timestamp":1658826646000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-19-3444-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9789811934438","9789811934445"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-19-3444-5_8","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"type":"print","value":"2190-3018"},{"type":"electronic","value":"2190-3026"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"27 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}