{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T05:56:21Z","timestamp":1761630981276,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030954048"},{"type":"electronic","value":"9783030954055"}],"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\/978-3-030-95405-5_24","type":"book-chapter","created":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T19:03:13Z","timestamp":1643655793000},"page":"341-352","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["PS-QMix: A Parallel Learning Framework for Q-Mix Using Parameter Server"],"prefix":"10.1007","author":[{"given":"Xunyun","family":"Liu","sequence":"first","affiliation":[]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Boren","family":"Xiao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,31]]},"reference":[{"unstructured":"Assran, M., Romoff, J., Ballas, N., Pineau, J., Rabbat, M.: Gossip-based actor-learner architectures for deep reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 32, pp. 13320\u201313330 (2019)","key":"24_CR1"},{"unstructured":"Babaeizadeh, M., Frosio, I., Tyree, S., Clemons, J., Kautz, J.: GA3C: GPU-based A3C for deep reinforcement learning (2016)","key":"24_CR2"},{"unstructured":"Bansal, T., Pachocki, J., Sidor, S., Sutskever, I., Mordatch, I.: Emergent complexity via multi-agent competition. In: International Conference on Learning Representations (2017)","key":"24_CR3"},{"issue":"2","key":"24_CR4","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., Schutter, B.D.: A comprehensive survey of multiagent reinforcement learning. Syst. Man Cybern. 38(2), 156\u2013172 (2008)","journal-title":"Syst. Man Cybern."},{"issue":"1","key":"24_CR5","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TII.2012.2219061","volume":"9","author":"Y Cao","year":"2013","unstructured":"Cao, Y., Yu, W., Ren, W., Chen, G.: An overview of recent progress in the study of distributed multi-agent coordination. IEEE Trans. Industr. Inf. 9(1), 427\u2013438 (2013)","journal-title":"IEEE Trans. Industr. Inf."},{"unstructured":"Chang, Y.H., Ho, T., Kaelbling, L.P.: All learning is local: multi-agent learning in global reward games. In: Advances in Neural Information Processing Systems 16, vol. 16, pp. 807\u2013814 (2003)","key":"24_CR6"},{"unstructured":"Espeholt, L., Marinier, R., Stanczyk, P., Wang, K., Michalski, M.: SEED RL: scalable and efficient Deep-RL with accelerated central inference. In: ICLR 2020: Eighth International Conference on Learning Representations (2020)","key":"24_CR7"},{"unstructured":"Espeholt, L., et al.: IMPALA: scalable distributed Deep-RL with importance weighted actor-learner architectures. In: International Conference on Machine Learning, pp. 1406\u20131415 (2018)","key":"24_CR8"},{"doi-asserted-by":"crossref","unstructured":"Foerster, J.N., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: AAAI, pp. 2974\u20132982 (2018)","key":"24_CR9","DOI":"10.1609\/aaai.v32i1.11794"},{"doi-asserted-by":"crossref","unstructured":"Grounds, M., Kudenko, D.: Parallel reinforcement learning with linear function approximation. In: Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems, p. 45 (2007)","key":"24_CR10","DOI":"10.1145\/1329125.1329179"},{"unstructured":"Ha, D., Dai, A., Le, Q.V.: Hypernetworks (2016)","key":"24_CR11"},{"unstructured":"Horgan, D., et al.: Distributed prioritized experience replay. In: International Conference on Learning Representations (2018)","key":"24_CR12"},{"unstructured":"H\u00fcttenrauch, M., Sosic, A., Neumann, G.: Guided deep reinforcement learning for swarm systems. CoRR abs\/1709.06011 (2017). http:\/\/arxiv.org\/abs\/1709.06011","key":"24_CR13"},{"key":"24_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-3-642-29946-9_30","volume-title":"Recent Advances in Reinforcement Learning","author":"Y Li","year":"2012","unstructured":"Li, Y., Schuurmans, D.: MapReduce for parallel reinforcement learning. In: Sanner, S., Hutter, M. (eds.) EWRL 2011. LNCS (LNAI), vol. 7188, pp. 309\u2013320. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-29946-9_30"},{"unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: ICLR 2016: International Conference on Learning Representations 2016 (2016)","key":"24_CR15"},{"unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, O.P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol. 30, pp. 6379\u20136390 (2017)","key":"24_CR16"},{"unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: ICML 2016 Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, pp. 1928\u20131937 (2016)","key":"24_CR17"},{"issue":"7540","key":"24_CR18","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"unstructured":"Moravc\u00edk, M., et al.: DeepStack: expert-level artificial intelligence in no-limit poker. CoRR abs\/1701.01724 (2017). http:\/\/arxiv.org\/abs\/1701.01724","key":"24_CR19"},{"unstructured":"Moritz, P., et al.: Ray: a distributed framework for emerging AI applications. In: OSDI 2018 Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation, pp. 561\u2013577 (2018)","key":"24_CR20"},{"unstructured":"Nair, A., et al.: Massively parallel methods for deep reinforcement learning. arXiv preprint arXiv:1507.04296 (2015)","key":"24_CR21"},{"unstructured":"Pesce, E., Montana, G.: Improving coordination in multi-agent deep reinforcement learning through memory-driven communication (2019)","key":"24_CR22"},{"unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4292\u20134301 (2018)","key":"24_CR23"},{"unstructured":"Samvelyan, M., et al.: The StarCraft multi-agent challenge. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, pp. 2186\u20132188 (2019)","key":"24_CR24"},{"issue":"7587","key":"24_CR25","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"issue":"7676","key":"24_CR26","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"},{"issue":"3","key":"24_CR27","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1023\/A:1008942012299","volume":"8","author":"P Stone","year":"2000","unstructured":"Stone, P., Veloso, M.: Multiagent systems: a survey from a machine learning perspective. Auton. Robot. 8(3), 345\u2013383 (2000)","journal-title":"Auton. Robot."},{"unstructured":"Sunehag, P., 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, pp. 2085\u20132087 (2018)","key":"24_CR28"},{"unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction (1988)","key":"24_CR29"},{"issue":"4","key":"24_CR30","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"},{"unstructured":"Tan, M.: Multi-agent reinforcement learning: independent vs. cooperative agents. In: ICML 1993 Proceedings of the Tenth International Conference on International Conference on Machine Learning, pp. 487\u2013494 (1997)","key":"24_CR31"},{"issue":"3","key":"24_CR32","first-page":"185","volume":"16","author":"JN Tsitsiklis","year":"1994","unstructured":"Tsitsiklis, J.N.: Asynchronous stochastic approximation and q-learning. Mach. Learn. 16(3), 185\u2013202 (1994)","journal-title":"Mach. Learn."},{"issue":"7782","key":"24_CR33","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"},{"issue":"2","key":"24_CR34","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/j.eswa.2005.04.039","volume":"29","author":"W Ying","year":"2005","unstructured":"Ying, W., Dayong, S.: Multi-agent framework for third party logistics in e-commerce. Expert Syst. Appl. 29(2), 431\u2013436 (2005)","journal-title":"Expert Syst. Appl."}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-95405-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,25]],"date-time":"2023-01-25T09:59:36Z","timestamp":1674640776000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-95405-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030954048","9783030954055"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-95405-5_24","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":"31 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sydney, NSW","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"2 February 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 February 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/adma2021.net\/","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":"CMT3","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"116","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":"26","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":"35","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":"22% - 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":"5","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}