{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T12:43:09Z","timestamp":1746708189222,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030862602"},{"type":"electronic","value":"9783030862619"}],"license":[{"start":{"date-parts":[[2021,9,2]],"date-time":"2021-09-02T00:00:00Z","timestamp":1630540800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,2]],"date-time":"2021-09-02T00:00:00Z","timestamp":1630540800000},"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\/978-3-030-86261-9_6","type":"book-chapter","created":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T13:04:13Z","timestamp":1630501453000},"page":"56-66","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Byzantine Resilient Aggregation in\u00a0Distributed Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Jiani","family":"Li","sequence":"first","affiliation":[]},{"given":"Feiyang","family":"Cai","sequence":"additional","affiliation":[]},{"given":"Xenofon","family":"Koutsoukos","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Sayed, A.H., Tu, S.Y., Chen, J., Zhao, X., Towfic, Z.J.: Diffusion strategies for adaptation and learning over networks: an examination of distributed strategies and network behavior. IEEE Signal Process. Mag. 30(3), 155\u2013171 (2013)","DOI":"10.1109\/MSP.2012.2231991"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, K., Yang, Z., Liu, H., Zhan g, T., Basar, T.: Fully decentralized multi-agent reinforcement learning with networked agents. In: ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, 10\u201315 July 2018, pp. 5867\u20135876 (2018)","DOI":"10.1109\/CDC.2018.8619581"},{"key":"6_CR3","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: JMLR Workshop and Conference Proceedings of, ICML 2016, New York City, NY, USA, 19-24 June 2016, vol.\u00a048, pp. 1928\u20131937. JMLR.org (2016)"},{"key":"6_CR4","unstructured":"Espeholt, L., et al.: IMPALA: scalable distributed Deep-RL with importance weighted actor-learner architectures. In: ICML 2018, Stockholm, Sweden, 10-15 July 2018"},{"key":"6_CR5","unstructured":"Blanchard, P., El Mhamdi, E.M., Guerraoui, R., Stainer, J.: Machine learning with adversaries: byzantine tolerant gradient descent. In: Annual Conference on Neural Information Processing Systems, pp. 118\u2013128 (2017)"},{"key":"6_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TSIPN.2019.2957731","volume":"6","author":"J Li","year":"2020","unstructured":"Li, J., Abbas, W., Koutsoukos, X.: Resilient distributed diffusion in networks with adversaries. IEEE Trans. Signal Inf. Process. over Netw. 6, 1\u201317 (2020)","journal-title":"IEEE Trans. Signal Inf. Process. over Netw."},{"key":"6_CR7","unstructured":"Yin, D., Chen, Y., Kannan, R., Bartlett, P.: Byzantine-robust distributed learning: towards optimal statistical rates. In: ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, 10-15 July 2018, pp. 5636\u20135645 (2018)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Yang, Z., Bajwa, W.U.: ByRDiE: byzantine-resilient distributed coordinate descent for decentralized learning. IEEE Trans. Signal Info. Process. Over Netw. 5(4), 611\u2013627 (2019)","DOI":"10.1109\/TSIPN.2019.2928176"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., Su, L., Xu, J.: Distributed statistical machine learning in adversarial settings: byzantine gradient descent. In: Proceedings of the ACM on Measurement and Analysis of Computing Systems, vol. 1, no. 2, pp. 44:1\u201344:25, December 2017","DOI":"10.1145\/3154503"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Li, J., Abbas, W., Shabbir, M., Koutsoukos, X.: Resilient distributed diffusion for multi-robot systems using centerpoint. In: Proceedings of Robotics: Science and Systems, Corvalis, Oregon, USA, July 2020","DOI":"10.15607\/RSS.2020.XVI.021"},{"key":"6_CR11","unstructured":"Li, J., Abbas, W., Koutsoukos, X.: Byzantine resilient distributed multi-task learning. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems, 6-12 December 2020 (2020)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Lin, Y., Gade, S., Sandhu, R., Liu, J.: Toward resilient multi-agent actor-critic algorithms for distributed reinforcement learning. In: 2020 American Control Conference, ACC 2020, Denver, CO, USA, 1-3 July 2020, pp. 3953\u20133958. IEEE (2020)","DOI":"10.23919\/ACC45564.2020.9147381"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Xie, Y., Mou, S., Sundaram, S.: Towards resilience for multi-agent QD-learning. CoRR, abs\/2104.03153 (2021)","DOI":"10.1109\/CDC45484.2021.9683145"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Macua, S.V., et.al.: Distributed policy evaluation under multiple behavior strategies. IEEE Trans. Automat. Contr. 60(5), 1260\u20131274 (2015)","DOI":"10.1109\/TAC.2014.2368731"},{"key":"6_CR15","unstructured":"Nair, A., et\u00a0al.: Massively parallel methods for deep reinforcement learning. CoRR, abs\/1507.04296 (2015)"},{"key":"6_CR16","unstructured":"Zhang, K., Yang, Z., Basar, T.: Multi-agent reinforcement learning: a selective overview of theories and algorithms. CoRR, abs\/1911.10635 (2019)"},{"key":"6_CR17","unstructured":"Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, 19-24 June 2016, vol.\u00a048 of JMLR Workshop and Conference Proceedings. JMLR.org (2016)"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Kar, S., Moura, J.M., Poor, H.V.: QD-learning: a collaborative distributed strategy for multi-agent reinforcement learning through Consensus + Innovations. IEEE Trans. Signal Process. 61(7), 1848\u20131862 (2013)","DOI":"10.1109\/TSP.2013.2241057"},{"key":"6_CR19","unstructured":"Macua, S.V., Tukiainen, A., Hern\u00e1ndez, D.G.O., Baldazo, D., de Cote, E.M., Zazo, S.: Diff-dac: distributed actor-critic for multitask deep reinforcement learning. CoRR, abs\/1710.10363 (2017)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. In: Machine Learning, pp. 279\u2013292 (1992)","DOI":"10.1023\/A:1022676722315"},{"key":"6_CR21","unstructured":"Mnih, V., et\u00a0al.: Playing atari with deep reinforcement learning. CoRR, abs\/1312.5602 (2013)"},{"key":"6_CR22","unstructured":"Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems 12, Denver, Colorado, USA, pp. 1057\u20131063 (1999)"},{"key":"6_CR23","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. In: ICLR 2016, San Juan, Puerto Rico, 2-4 May 2016, Conference Track Proceedings (2016)"},{"key":"6_CR24","unstructured":"Brockman, G.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"6_CR25","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: ICLR (2016)"},{"key":"6_CR26","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR 2015, San Diego, CA, USA, 7-9 May 2015"}],"container-title":["Lecture Notes in Networks and Systems","Distributed Computing and Artificial Intelligence, Volume 1: 18th International Conference"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86261-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T11:58:56Z","timestamp":1673179136000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86261-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,2]]},"ISBN":["9783030862602","9783030862619"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86261-9_6","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2021,9,2]]},"assertion":[{"value":"2 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Distributed Computing and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salamanca","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dcai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.dcai-conference.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}