{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T17:00:08Z","timestamp":1743094808621,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030953836"},{"type":"electronic","value":"9783030953843"}],"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\/978-3-030-95384-3_41","type":"book-chapter","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T08:20:55Z","timestamp":1645518055000},"page":"660-675","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Security Analysis of Poisoning Attacks Against Multi-agent Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Zhiqiang","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingxiao","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yike","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Endong","family":"Tong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjia","family":"Niu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiqiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,2,23]]},"reference":[{"issue":"7676","key":"41_CR1","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Xu, Z., Chen, J., Tomizuka, M.: Guided policy search model-based reinforcement learning for urban autonomous driving. arXiv preprint arXiv:2005.03076 (2020)","DOI":"10.1109\/ITSC.2019.8917306"},{"key":"41_CR3","doi-asserted-by":"crossref","unstructured":"Yang, B., Liu, M.: Keeping in touch with collaborative UAVs: a deep reinforcement learning approach. In: IJCAI, pp. 562\u2013568 (2018)","DOI":"10.24963\/ijcai.2018\/78"},{"key":"41_CR4","unstructured":"Chen, G.: A new framework for multi-agent reinforcement learning\u2013centralized training and exploration with decentralized execution via policy distillation. In: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, pp. 1801\u20131803 (2020)"},{"issue":"7782","key":"41_CR5","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"41_CR6","unstructured":"Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)"},{"issue":"4","key":"41_CR7","doi-asserted-by":"publisher","first-page":"e0172395","DOI":"10.1371\/journal.pone.0172395","volume":"12","author":"A Tampuu","year":"2017","unstructured":"Tampuu, A., et al.: Multiagent cooperation and competition with deep reinforcement learning. PloS one 12(4), e0172395 (2017)","journal-title":"PloS one"},{"key":"41_CR8","unstructured":"Wai, H.T., Yang, Z., Wang, Z., Hong, M.: Multi-agent reinforcement learning via double averaging primal-dual optimization. In: NeurIPS (2018)"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Abouheaf, M., Gueaieb, W.: Multi-agent reinforcement learning approach based on reduced value function approximations. In: 2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS), pp. 111\u2013116. IEEE (2017)","DOI":"10.1109\/IRIS.2017.8250107"},{"key":"41_CR10","unstructured":"Foerster, J., et al.: Stabilising experience replay for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 1146\u20131155. PMLR (2017)"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"41_CR12","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6382\u20136393 (2017)"},{"key":"41_CR13","unstructured":"Iqbal, S., Sha, F.: Actor-attention-critic for multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 2961\u20132970. PMLR (2019)"},{"key":"41_CR14","unstructured":"Huang, S., Papernot, N., Goodfellow, I., Duan, Y., Abbeel, P.: Adversarial attacks on neural network policies. arXiv preprint arXiv:1702.02284 (2017)"},{"key":"41_CR15","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Niu, W., Liu, J., Chen, T., Han, Z.: A pca-based model to predict adversarial examples on q-learning of path finding. In: 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), pp. 773\u2013780. IEEE (2018)","DOI":"10.1109\/DSC.2018.00125"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Lin, Y.C., Hong, Z.W., Liao, Y.H., Shih, M.L., Liu, M.Y., Sun, M.: Tactics of adversarial attack on deep reinforcement learning agents. arXiv preprint arXiv:1703.06748 (2017)","DOI":"10.24963\/ijcai.2017\/525"},{"key":"41_CR17","unstructured":"Pan, X., Wang, W., Zhang, X., Li, B., Yi, J., Song, D.: How you act tells a lot: Privacy-leaking attack on deep reinforcement learning. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, pp. 368\u2013376 (2019)"},{"key":"41_CR18","unstructured":"Ma, Y., Zhang, X., Sun, W., Zhu, X.: Policy poisoning in batch reinforcement learning and control. arXiv preprint arXiv:1910.05821 (2019)"},{"key":"41_CR19","unstructured":"Zhang, X., Ma, Y., Singla, A., Zhu, X.: Adaptive reward-poisoning attacks against reinforcement learning. In: International Conference on Machine Learning, pp. 11225\u201311234. PMLR (2020)"},{"key":"41_CR20","unstructured":"Rakhsha, A., Radanovic, G., Devidze, R., Zhu, X., Singla, A.: Policy teaching in reinforcement learning via environment poisoning attacks. arXiv preprint arXiv:2011.10824 (2020)"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Machine Learning Proceedings 1994, pp. 157\u2013163. Elsevier (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"41_CR22","unstructured":"Konda, V.R., Tsitsiklis, J.N.: Actor-critic algorithms. In: Advances in Neural Information Processing Systems, pp. 1008\u20131014 (2000)"},{"key":"41_CR23","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018)"},{"key":"41_CR24","unstructured":"Multi-Agent Particle Environment. https:\/\/github.com\/openai\/multiagent-particle-envs, Accessed 20 Juy 2021"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-95384-3_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T17:16:21Z","timestamp":1674839781000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-95384-3_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030953836","9783030953843"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-95384-3_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/nsclab.org\/ica3pp2021\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"403","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"145","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"36% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.12","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.27","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}