{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:07:43Z","timestamp":1742962063956,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031301049"},{"type":"electronic","value":"9783031301056"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-30105-6_7","type":"book-chapter","created":{"date-parts":[[2023,4,12]],"date-time":"2023-04-12T20:31:55Z","timestamp":1681331515000},"page":"76-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Agent Hyper-Attention Policy Optimization"],"prefix":"10.1007","author":[{"given":"Bin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dapeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunpeng","family":"Bai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoliang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,13]]},"reference":[{"key":"7_CR1","unstructured":"Chu, X.: Policy optimization with penalized point probability distance: an alternative to proximal policy optimization. arXiv preprint arXiv:1807.00442 (2018)"},{"key":"7_CR2","unstructured":"Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: NIPS (2016)"},{"key":"7_CR3","unstructured":"Engstrom, L., Ilyas, A., Santurkar, S., Tsipras, D., Janoos, F., Rudolph, L., Madry, A.: Implementation matters in deep policy gradients: A case study on ppo and trpo. arXiv preprint arXiv:2005.12729 (2020)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Feng, Y., You, H., Zhang, Z., Ji, R., Gao, Y.: Hypergraph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., et al.: Counterfactual multi-agent policy gradients. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"7_CR6","unstructured":"Ha, D., Dai, A., Le, Q.V.: Hypernetworks. arXiv preprint arXiv:1609.09106 (2016)"},{"key":"7_CR7","unstructured":"Hu, J., Jiang, S., Harding, S.A., Wu, H., Liao, S.: Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning. arXiv preprint arXiv:2102.03479 (2021)"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Y., Xie, K., Bharadhwaj, H., Shkurti, F.: Continual model-based reinforcement learning with hypernetworks. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 799\u2013805. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9560793"},{"key":"7_CR9","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":"7_CR10","unstructured":"Kuba, J.G., Chen, R., Wen, M., Wen, Y., et al.: Trust region policy optimisation in multi-agent reinforcement learning. arXiv preprint arXiv:2109.11251 (2021)"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, W., Hu, Y., Hao, J., Chen, X., Gao, Y.: Multi-agent game abstraction via graph attention neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence (2020)","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"7_CR12","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems (2017)"},{"key":"7_CR13","unstructured":"Peng, Z., Li, Q., Hui, K.M., Liu, C., Zhou, B.: Learning to simulate self-driven particles system with coordinated policy optimization. In: Advances in Neural Information Processing Systems, vol. 34, pp. 10784\u201310797 (2021)"},{"key":"7_CR14","unstructured":"Rashid, T., Samvelyan, M., Witt, C.S., Farquhar, G., Foerster, J.N., Whiteson, S.: Qmix: monotonic value function factorisation for deep multi-agent reinforcement learning. arXiv:abs\/1803.11485 (2018)"},{"key":"7_CR15","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge. arXiv:abs\/1902.04043 (2019)"},{"key":"7_CR16","unstructured":"Sarafian, E., Keynan, S., Kraus, S.: Recomposing the reinforcement learning building blocks with hypernetworks. In: International Conference on Machine Learning, pp. 9301\u20139312. PMLR (2021)"},{"key":"7_CR17","unstructured":"Schulman, J., Levine, S., Abbeel, P., et al.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"7_CR18","unstructured":"Schulman, J., Moritz, P., Levine, S., et al.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)"},{"key":"7_CR19","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"7_CR20","unstructured":"Son, K., Kim, D., et al.: Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. arXiv:abs\/1905.05408 (2019)"},{"key":"7_CR21","doi-asserted-by":"crossref","unstructured":"Su, J., Adams, S., Beling, P.A.: Value-decomposition multi-agent actor-critics. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i13.17353"},{"key":"7_CR22","unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv:abs\/1706.05296 (2018)"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Tampuu, A., Matiisen, T., Kodelja, D., Kuzovkin, I., et al.: Multiagent cooperation and competition with deep reinforcement learning. PLoS ONE (2017)","DOI":"10.1371\/journal.pone.0172395"},{"key":"7_CR24","unstructured":"Tao, N., Baxter, J., Weaver, L.: A multi-agent, policy-gradient approach to network routing. In: Proceedings of the 18th International Conference on Machine Learning. Citeseer (2001)"},{"key":"7_CR25","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"issue":"7782","key":"7_CR26","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., Babuschkin, I., Czarnecki, W.M., et al.: Grandmaster level in starcraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"7_CR27","unstructured":"Wang, J., Ren, Z., Liu, T., et al.: QPLEX: duplex dueling multi-agent q-learning. In: International Conference on Learning Representations, ICLR (2021)"},{"key":"7_CR28","unstructured":"Wang, Y., He, H., Tan, X.: Truly proximal policy optimization. In: Uncertainty in Artificial Intelligence, pp. 113\u2013122. PMLR (2020)"},{"key":"7_CR29","unstructured":"de Witt, C.S., Gupta, T., Makoviichuk, D., Makoviychuk, V., Torr, P.H., Sun, M., Whiteson, S.: Is independent learning all you need in the starcraft multi-agent challenge? arXiv preprint arXiv:2011.09533 (2020)"},{"key":"7_CR30","unstructured":"Yang, Y., Luo, R., Li, M., et al.: Mean field multi-agent reinforcement learning. In: International Conference on Machine Learning. PMLR (2018)"},{"key":"7_CR31","unstructured":"Yu, C., Velu, A., Vinitsky, E., Wang, Y., et al.: The surprising effectiveness of PPO in cooperative, multi-agent games. arXiv preprint arXiv:2103.01955 (2021)"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, B., Bai, Y., Xu, Z., Li, D., Fan, G.: Efficient cooperation strategy generation in multi-agent video games via hypergraph neural network. arXiv preprint arXiv:2203.03265 (2022)","DOI":"10.1007\/978-3-031-30108-7_19"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-30105-6_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T16:15:26Z","timestamp":1702224926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30105-6_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031301049","9783031301056"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30105-6_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"13 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Delhi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iconip2022.apnns.org\/","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":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"810","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":"359","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":"44% - 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":"2.65","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":"3","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)"}},{"value":"ICONIP 2022 consists of a two-volume set, LNCS & CCIS, which includes 146 and 213 papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}