{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T19:58:34Z","timestamp":1773950314553,"version":"3.50.1"},"reference-count":92,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T00:00:00Z","timestamp":1711065600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T00:00:00Z","timestamp":1711065600000},"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":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s11432-023-3853-y","type":"journal-article","created":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T01:35:18Z","timestamp":1711330518000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Robust cooperative multi-agent reinforcement learning via multi-view message certification"],"prefix":"10.1007","volume":"67","author":[{"given":"Lei","family":"Yuan","sequence":"first","affiliation":[]},{"given":"Tao","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Lihe","family":"Li","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Zongzhang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yang","family":"Yu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,3,22]]},"reference":[{"key":"3853_CR1","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu L, Babuska R, de Schutter B. A comprehensive survey of multiagent reinforcement learning. IEEE Trans Syst Man Cybern C, 2008, 38: 156\u2013172","journal-title":"IEEE Trans Syst Man Cybern C"},{"key":"3853_CR2","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-030-60990-0_12","volume-title":"Handbook of Reinforcement Learning and Control","author":"K Zhang","year":"2021","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. Berlin: Springer, 2021. 321\u2013384"},{"key":"3853_CR3","doi-asserted-by":"publisher","first-page":"13677","DOI":"10.1007\/s10489-022-04105-y","volume":"53","author":"A Oroojlooy","year":"2023","unstructured":"Oroojlooy A, Hajinezhad D. A review of cooperative multi-agent deep reinforcement learning. Appl Intell, 2023, 53: 13677\u201313722","journal-title":"Appl Intell"},{"key":"3853_CR4","unstructured":"Wang J, Xu W, Gu Y, et al. Multi-agent reinforcement learning for active voltage control on power distribution networks. In: Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 2021. 3271\u20133284"},{"key":"3853_CR5","doi-asserted-by":"publisher","first-page":"7086","DOI":"10.1109\/TII.2022.3143175","volume":"18","author":"W J Yun","year":"2022","unstructured":"Yun W J, Park S, Kim J, et al. Cooperative multiagent deep reinforcement learning for reliable surveillance via autonomous multi-UAV control. IEEE Trans Ind Inf, 2022, 18: 7086\u20137096","journal-title":"IEEE Trans Ind Inf"},{"key":"3853_CR6","unstructured":"Xue K, Xu J, Yuan L, et al. Multi-agent dynamic algorithm configuration. In: Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), 2022"},{"key":"3853_CR7","unstructured":"Sunehag P, Lever G, Gruslys A, 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), 2018. 2085\u20132087"},{"key":"3853_CR8","unstructured":"Rashid T, Samvelyan M, Schroeder C, et al. QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: Proceedings of the 35th International Conference on Machine Learning (ICML), 2018. 4295\u20134304"},{"key":"3853_CR9","unstructured":"Wang J, Ren Z, Liu T, et al. QPLEX: duplex dueling multi-agent Q-learning. In: Proceedings of the International Conference on Learning Representations (ICLR), 2021"},{"key":"3853_CR10","unstructured":"Lowe R, Wu Y, Tamar A, et al. Multi-agent actor-critic for mixed cooperative-competitive environments. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS), 2017. 6382\u20136393"},{"key":"3853_CR11","unstructured":"Yu C, Velu A, Vinitsky E, et al. The surprising effectiveness of PPO in cooperative multi-agent games. 2021. ArXiv:2103.01955"},{"key":"3853_CR12","unstructured":"Ye J, Li C, Wang J, et al. Towards global optimality in cooperative marl with sequential transformation. 2022. ArXiv:2207.11143"},{"key":"3853_CR13","unstructured":"Wang Y, Han B, Wang T, et al. DOP: off-policy multi-agent decomposed policy gradients. In: Proceedings of the International Conference on Learning Representations (ICLR), 2021"},{"key":"3853_CR14","unstructured":"Cao J, Yuan L, Wang J, et al. LINDA: multi-agent local information decomposition for awareness of teammates. 2021. ArXiv:2109.12508"},{"key":"3853_CR15","doi-asserted-by":"crossref","unstructured":"Yuan L, Wang C, Wang J, et al. Multi-agent concentrative coordination with decentralized task representation. In: Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI), 2022. 599\u2013605","DOI":"10.24963\/ijcai.2022\/85"},{"key":"3853_CR16","unstructured":"Wen M, Kuba J G, Lin R, et al. Multi-agent reinforcement learning is a sequence modeling problem. In: Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), 2022"},{"key":"3853_CR17","unstructured":"Papoudakis G, Christianos F, Schafer L, et al. Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks. In: Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 2021"},{"key":"3853_CR18","unstructured":"Gorsane R, Mahjoub O, de Kock R, et al. Towards a standardised performance evaluation protocol for cooperative MARL. In: Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), 2022"},{"key":"3853_CR19","doi-asserted-by":"publisher","first-page":"276","DOI":"10.3390\/make4010013","volume":"4","author":"J Moos","year":"2022","unstructured":"Moos J, Hansel K, Abdulsamad H, et al. Robust reinforcement learning: a review of foundations and recent advances. Mach Learn Know Extr, 2022, 4: 276\u2013315","journal-title":"Mach Learn Know Extr"},{"key":"3853_CR20","doi-asserted-by":"crossref","unstructured":"Guo J, Chen Y, Hao Y, et al. Towards comprehensive testing on the robustness of cooperative multi-agent reinforcement learning. 2022. ArXiv:2204.07932","DOI":"10.1109\/CVPRW56347.2022.00022"},{"key":"3853_CR21","unstructured":"Pinto L, Davidson J, Sukthankar R, et al. Robust adversarial reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning (ICML), 2017. 2817\u20132826"},{"key":"3853_CR22","unstructured":"Zhang H, Chen H, Xiao C, et al. Robust deep reinforcement learning against adversarial perturbations on state observations. In: Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS), 2020. 21024\u201321037"},{"key":"3853_CR23","unstructured":"Vinitsky E, Du Y, Parvate K, et al. Robust reinforcement learning using adversarial populations. 2020. ArXiv:2008.01825"},{"key":"3853_CR24","doi-asserted-by":"crossref","unstructured":"Song Y, Schneider J. Robust reinforcement learning via genetic curriculum. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2022. 5560\u20135566","DOI":"10.1109\/ICRA46639.2022.9812420"},{"key":"3853_CR25","unstructured":"Yu J, Gehring C, Sch\u00e4fer F, et al. Robust reinforcement learning: a constrained game-theoretic approach. In: Proceedings of the 3rd Conference on Learning for Dynamics and Control (L4DC), 2021. 1242\u20131254"},{"key":"3853_CR26","unstructured":"Oikarinen T, Zhang W, Megretski A, et al. Robust deep reinforcement learning through adversarial loss. In: Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 2021. 26156\u201326167"},{"key":"3853_CR27","unstructured":"Sun Y, Zheng R, Liang Y, et al. Who is the strongest enemy? Towards optimal and efficient evasion attacks in deep RL. In: Proceedings of the 10th International Conference on Learning Representations (ICLR), 2021"},{"key":"3853_CR28","unstructured":"Wu J, Vorobeychik Y. Robust deep reinforcement learning through bootstrapped opportunistic curriculum. In: Proceedings of the 39th International Conference on Machine Learning (ICML), 2022. 24177\u201324211"},{"key":"3853_CR29","doi-asserted-by":"publisher","first-page":"4184","DOI":"10.1109\/TNNLS.2021.3056046","volume":"33","author":"M Everett","year":"2022","unstructured":"Everett M, L\u00fctjens B, How J P. Certifiable robustness to adversarial state uncertainty in deep reinforcement learning. IEEE Trans Neural Netw Learn Syst, 2022, 33: 4184\u20134198","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"3853_CR30","unstructured":"Wu F, Li L, Huang Z, et al. CROP: certifying robust policies for reinforcement learning through functional smoothing. In: Proceedings of the International Conference on Learning Representations (ICLR), 2021"},{"key":"3853_CR31","doi-asserted-by":"crossref","unstructured":"Sun C, Kim D K, How J P. ROMAX: certifiably robust deep multiagent reinforcement learning via convex relaxation. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2022. 5503\u20135510","DOI":"10.1109\/ICRA46639.2022.9812321"},{"key":"3853_CR32","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, 2018, 6: 28573\u201328593","journal-title":"IEEE Access"},{"key":"3853_CR33","unstructured":"Christianos F, Papoudakis G, Rahman A, et al. Scaling multi-agent reinforcement learning with selective parameter sharing. In: Proceedings of the 38th International Conference on Machine Learning (ICML), 2021. 1989\u20131998"},{"key":"3853_CR34","unstructured":"van der Heiden T, Salge C, Gavves E, et al. Robust multi-agent reinforcement learning with social empowerment for coordination and communication. 2020. ArXiv:2012.08255"},{"key":"3853_CR35","doi-asserted-by":"crossref","unstructured":"Li S, Wu Y, Cui X, et al. Robust multi-agent reinforcement learning via minimax deep deterministic policy gradient. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2019. 4213\u20134220","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"3853_CR36","unstructured":"Zhou Z, Liu G. RoMFAC: a robust mean-field actor-critic reinforcement learning against adversarial perturbations on states. 2022. ArXiv:2205.07229"},{"key":"3853_CR37","unstructured":"Zhang K, Sun T, Tao Y, et al. Robust multi-agent reinforcement learning with model uncertainty. In: Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS), 2020. 10571\u201310583"},{"key":"3853_CR38","unstructured":"Hu Y, Shao K, Li D, et al. Robust multi-agent reinforcement learning driven by correlated equilibrium. In: Proceedings of the International Conference on Learning Representations (ICLR), 2021"},{"key":"3853_CR39","unstructured":"Hu Y, Zhang Z. Sparse adversarial attack in multi-agent reinforcement learning. 2022. ArXiv:2205.09362"},{"key":"3853_CR40","unstructured":"Zhu C, Dastani M, Wang S. A survey of multi-agent reinforcement learning with communication. 2022. ArXiv:2203.08975"},{"key":"3853_CR41","unstructured":"Blumenkamp J, Prorok A. The emergence of adversarial communication in multi-agent reinforcement learning. In: Proceedings of the 4th Conference on Robot Learning (CoRL), 2021. 1394\u20131414"},{"key":"3853_CR42","unstructured":"Sun Y, Zheng R, Hassanzadeh P, et al. Certifiably robust policy learning against adversarial communication in multi-agent systems. 2022. ArXiv:2206.10158"},{"key":"3853_CR43","unstructured":"Xue W, Qiu W, An B, et al. Mis-spoke or mis-lead: achieving robustness in multi-agent communicative reinforcement learning. In: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2022. 1418\u20131426"},{"key":"3853_CR44","volume-title":"Information Theory, Inference, and Learning Algorithms","author":"D J C MacKay","year":"2003","unstructured":"MacKay D J C. Information Theory, Inference, and Learning Algorithms. Cambridge: Cambridge University Press, 2003"},{"key":"3853_CR45","unstructured":"Wang T, Wang J, Zheng C, et al. Learning nearly decomposable value functions via communication minimization. In: Proceedings of the 8th International Conference on Learning Representations (ICLR), 2020"},{"key":"3853_CR46","unstructured":"Das A, Gervet T, Romoff J, et al. TarMAC: targeted multi-agent communication. In: Proceedings of the 36th International Conference on Machine Learning (ICML), 2019. 1538\u20131546"},{"key":"3853_CR47","unstructured":"Foerster J N, Assael Y M, de Freitas N, et al. Learning to communicate with deep multi-agent reinforcement learning. In: Proceedings of the 30th International Conference on Neural Information Processing Systems (NeurIPS), 2016. 2145\u20132153"},{"key":"3853_CR48","unstructured":"Sukhbaatar S, Szlam A, Fergus R. Learning multiagent communication with backpropagation. In: Proceedings of the 30th International Conference on Neural Information Processing Systems (NeurIPS), 2016. 2252\u20132260"},{"key":"3853_CR49","doi-asserted-by":"crossref","unstructured":"Mao H, Zhang Z, Xiao Z, et al. Learning agent communication under limited bandwidth by message pruning. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2020. 5142\u20135149","DOI":"10.1609\/aaai.v34i04.5957"},{"key":"3853_CR50","unstructured":"Ding Z, Huang T, Lu Z. Learning individually inferred communication for multi-agent cooperation. In: Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS), 2020"},{"key":"3853_CR51","doi-asserted-by":"crossref","unstructured":"Xue D, Yuan L, Zhang Z, et al. Efficient multi-agent communication via shapley message value. In: Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI), 2022. 578\u2013584","DOI":"10.24963\/ijcai.2022\/82"},{"key":"3853_CR52","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s10458-020-09455-w","volume":"34","author":"H Mao","year":"2020","unstructured":"Mao H, Zhang Z, Xiao Z, et al. Learning multi-agent communication with double attentional deep reinforcement learning. Auton Agent Multi-Ag, 2020, 34: 32","journal-title":"Auton Agent Multi-Ag"},{"key":"3853_CR53","unstructured":"Wang Y, Xu J, Wang Y, et al. ToM2C: target-oriented multi-agent communication and cooperation with theory of mind. In: Proceedings of the International Conference on Learning Representations (ICLR), 2021"},{"key":"3853_CR54","unstructured":"Zhang S Q, Zhang Q, Lin J. Efficient communication in multi-agent reinforcement learning via variance based control. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS), 2019. 3235\u20133244"},{"key":"3853_CR55","unstructured":"Zhang S Q, Zhang Q, Lin J. Succinct and robust multi-agent communication with temporal message control. In: Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS), 2020. 17271\u201317282"},{"key":"3853_CR56","doi-asserted-by":"crossref","unstructured":"Yuan L, Wang J, Zhang F, et al. Multi-agent incentive communication via decentralized teammate modeling. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence, 2022. 9466\u20139474","DOI":"10.1609\/aaai.v36i9.21179"},{"key":"3853_CR57","doi-asserted-by":"crossref","unstructured":"Pan X, Seita D, Gao Y, et al. Risk averse robust adversarial reinforcement learning. In: Proceedings of the International Conference on Robotics and Automation (ICRA), 2019. 8522\u20138528","DOI":"10.1109\/ICRA.2019.8794293"},{"key":"3853_CR58","unstructured":"Liang Y, Sun Y, Zheng R, et al. Efficient adversarial training without attacking: worst-case-aware robust reinforcement learning. In: Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), 2022"},{"key":"3853_CR59","unstructured":"Qin Z, Zhang K, Chen Y, et al. Learning safe multi-agent control with decentralized neural barrier certificates. In: Proceedings of the International Conference on Learning Representations (ICLR), 2020"},{"key":"3853_CR60","unstructured":"Wu F, Li L, Zhang H, et al. COPA: certifying robust policies for offline reinforcement learning against poisoning attacks. In: Proceedings of the International Conference on Learning Representations (ICLR), 2021"},{"key":"3853_CR61","doi-asserted-by":"crossref","unstructured":"Park H, Lee S, Lee J, et al. Learning by aligning: visible-infrared person re-identification using cross-modal correspondences. In: Proceedings of the International Conference on Computer Vision (ICCV), 2021. 12046\u201312055","DOI":"10.1109\/ICCV48922.2021.01183"},{"key":"3853_CR62","doi-asserted-by":"publisher","first-page":"2365","DOI":"10.1109\/TPAMI.2012.64","volume":"34","author":"N Chen","year":"2012","unstructured":"Chen N, Zhu J, Sun F, et al. Large-margin predictive latent subspace learning for multiview data analysis. IEEE Trans Pattern Anal Mach Intell, 2012, 34: 2365\u20132378","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3853_CR63","doi-asserted-by":"crossref","unstructured":"Xu J, Li W, Liu X, et al. Deep embedded complementary and interactive information for multi-view classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2020. 6494\u20136501","DOI":"10.1609\/aaai.v34i04.6122"},{"key":"3853_CR64","unstructured":"Kingma D P, Welling M. Auto-encoding variational Bayes. In: Proceedings of the International Conference on Learning Representations (ICLR), 2014"},{"key":"3853_CR65","unstructured":"Sohn K, Lee H, Yan X. Learning structured output representation using deep conditional generative models. In: Proceedings of the 28th International Conference on Neural Information Processing Systems (NeurIPS), 2015. 3483\u20133491"},{"key":"3853_CR66","unstructured":"Wu M, Goodman N. Multimodal generative models for scalable weakly-supervised learning. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS), 2018. 5580\u20135590"},{"key":"3853_CR67","unstructured":"Suzuki M, Nakayama K, Matsuo Y. Joint multimodal learning with deep generative models. 2016. ArXiv:1611.01891"},{"key":"3853_CR68","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.neucom.2021.03.090","volume":"448","author":"X Yan","year":"2021","unstructured":"Yan X, Hu S, Mao Y, et al. Deep multi-view learning methods: a review. Neurocomputing, 2021, 448: 106\u2013129","journal-title":"Neurocomputing"},{"key":"3853_CR69","doi-asserted-by":"publisher","first-page":"2939","DOI":"10.1007\/s00371-021-02166-7","volume":"38","author":"K Bayoudh","year":"2022","unstructured":"Bayoudh K, Knani R, Hamdaoui F, et al. A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Vis Comput, 2022, 38: 2939\u20132970","journal-title":"Vis Comput"},{"key":"3853_CR70","doi-asserted-by":"crossref","unstructured":"Ma M, Ren J, Zhao L, et al. SMIL: multimodal learning with severely missing modality. In: Proceedings of the 35th AAAI Conference on Artificial Intelligence, 2021. 2302\u20132310","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"3853_CR71","doi-asserted-by":"publisher","first-page":"5812","DOI":"10.1109\/TIP.2015.2490539","volume":"24","author":"C Xu","year":"2015","unstructured":"Xu C, Tao D, Xu C. Multi-view learning with incomplete views. IEEE Trans Image Process, 2015, 24: 5812\u20135825","journal-title":"IEEE Trans Image Process"},{"key":"3853_CR72","unstructured":"Li M, Wu L, Wang J, et al. Multi-view reinforcement learning. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS), 2019. 1420\u20131431"},{"key":"3853_CR73","unstructured":"Fan J, Li W. DRIBO: robust deep reinforcement learning via multi-view information bottleneck. In: Proceedings of the 39th International Conference on Machine Learning (ICML), 2022. 6074\u20136102"},{"key":"3853_CR74","unstructured":"Kinose A, Okada M, Okumura R, et al. Multi-view dreaming: multi-view world model with contrastive learning. 2022. ArXiv:2203.11024"},{"key":"3853_CR75","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","volume":"55","author":"S Gronauer","year":"2022","unstructured":"Gronauer S, Diepold K. Multi-agent deep reinforcement learning: a survey. Artif Intell Rev, 2022, 55: 895\u2013943","journal-title":"Artif Intell Rev"},{"key":"3853_CR76","unstructured":"Papoudakis G, Christianos F, Rahman A, et al. Dealing with non-stationarity in multi-agent deep reinforcement learning. 2019. ArXiv:1906.04737"},{"key":"3853_CR77","unstructured":"Wang J, Ren Z, Han B, et al. Towards understanding cooperative multi-agent Q-learning with value factorization. In: Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 2021. 29142\u201329155"},{"key":"3853_CR78","doi-asserted-by":"crossref","unstructured":"Lin J, Dzeparoska K, Zhang S Q, et al. On the robustness of cooperative multi-agent reinforcement learning. In: Proceedings of the IEEE Security and Privacy Workshops (SPW), 2020. 62\u201368","DOI":"10.1109\/SPW50608.2020.00027"},{"key":"3853_CR79","unstructured":"Mitchell R, Blumenkamp J, Prorok A. Gaussian process based message filtering for robust multi-agent cooperation in the presence of adversarial communication. 2020. ArXiv:2012.00508"},{"key":"3853_CR80","doi-asserted-by":"crossref","unstructured":"Tu J, Wang T, Wang J, et al. Adversarial attacks on multi-agent communication. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), 2021. 7768\u20137777","DOI":"10.1109\/ICCV48922.2021.00767"},{"key":"3853_CR81","doi-asserted-by":"crossref","unstructured":"Cho K, van Merri\u00ebnboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014. 1724\u20131734","DOI":"10.3115\/v1\/D14-1179"},{"key":"3853_CR82","unstructured":"Qiaoben Y, Ying C, Zhou X, et al. Understanding adversarial attacks on observations in deep reinforcement learning. 2021. ArXiv:2106.15860"},{"key":"3853_CR83","unstructured":"Xu M, Liu Z, Huang P, et al. Trustworthy reinforcement learning against intrinsic vulnerabilities: robustness, safety, and generalizability. 2022. ArXiv:2209.08025"},{"key":"3853_CR84","unstructured":"Goodfellow I J, Shlens J, Szegedy C. Explaining and harnessing adversarial examples. In: Proceedings of the International Conference on Learning Representations (ICLR), 2015"},{"key":"3853_CR85","unstructured":"Gowal S, Dvijotham K, Stanforth R, et al. On the effectiveness of interval bound propagation for training verifiably robust models. 2018. ArXiv:1810.12715"},{"key":"3853_CR86","doi-asserted-by":"publisher","first-page":"1863","DOI":"10.1109\/TKDE.2018.2872063","volume":"31","author":"Y Li","year":"2018","unstructured":"Li Y, Yang M, Zhang Z. A survey of multi-view representation learning. IEEE Trans Knowl Data Eng, 2018, 31: 1863\u20131883","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"3853_CR87","unstructured":"Hwang H, Kim G H, Hong S, et al. Multi-view representation learning via total correlation objective. In: Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS), 2021. 12194\u201312207"},{"key":"3853_CR88","unstructured":"Cao Y, Fleet D J. Generalized product of experts for automatic and principled fusion of Gaussian process predictions. 2014. ArXiv:1410.7827"},{"key":"3853_CR89","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1137\/0505030","volume":"5","author":"W Gautschi","year":"1974","unstructured":"Gautschi W. A harmonic mean inequality for the Gamma function. SIAM J Math Anal, 1974, 5: 278\u2013281","journal-title":"SIAM J Math Anal"},{"key":"3853_CR90","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.neucom.2016.01.031","volume":"190","author":"L Kraemer","year":"2016","unstructured":"Kraemer L, Banerjee B. Multi-agent reinforcement learning as a rehearsal for decentralized planning. Neurocomputing, 2016, 190: 82\u201394","journal-title":"Neurocomputing"},{"key":"3853_CR91","unstructured":"Lyu X, Xiao Y, Daley B, et al. Contrasting centralized and decentralized critics in multi-agent reinforcement learning. In: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS), 2021. 844\u2013852"},{"key":"3853_CR92","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1111\/1467-9868.00196","volume":"61","author":"M E Tipping","year":"1999","unstructured":"Tipping M E, Bishop C M. Probabilistic principal component analysis. J Royal Stat Soc B, 1999, 61: 611\u2013622","journal-title":"J Royal Stat Soc B"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-3853-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-023-3853-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-3853-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T19:45:29Z","timestamp":1747770329000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-023-3853-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,22]]},"references-count":92,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["3853"],"URL":"https:\/\/doi.org\/10.1007\/s11432-023-3853-y","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,22]]},"assertion":[{"value":"10 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"142102"}}