{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T11:46:40Z","timestamp":1743076000888,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030041786"},{"type":"electronic","value":"9783030041793"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-04179-3_63","type":"book-chapter","created":{"date-parts":[[2018,11,17]],"date-time":"2018-11-17T07:12:42Z","timestamp":1542438762000},"page":"711-721","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Asynchronous Methods for Multi-agent Deep Deterministic Policy Gradient"],"prefix":"10.1007","author":[{"given":"Xuesong","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhipeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiumei","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,18]]},"reference":[{"key":"63_CR1","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. J. Nature. 518, 529\u2013533 (2015)","journal-title":"J. Nature."},{"issue":"11","key":"63_CR2","doi-asserted-by":"publisher","first-page":"3698","DOI":"10.4249\/scholarpedia.3698","volume":"5","author":"J Peters","year":"2010","unstructured":"Peters, J.: Policy gradient methods. J. Scholarpedia 5(11), 3698 (2010)","journal-title":"J. Scholarpedia"},{"key":"63_CR3","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: International Conference on Learning Representations 2016, San Juan (2016)"},{"key":"63_CR4","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: International Conference on Learning Representations 2016, San Juan (2016)"},{"key":"63_CR5","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Learning Representations 2016, San Juan (2016)"},{"key":"63_CR6","unstructured":"Jaderberg, M., et al.: Reinforcement learning with unsupervised auxiliary tasks. In: 5th International Conference on Learning Representations, Toulon (2016)"},{"key":"63_CR7","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach (2017)"},{"key":"63_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/11564096_32","volume-title":"Machine Learning: ECML 2005","author":"M Riedmiller","year":"2005","unstructured":"Riedmiller, M.: Neural fitted Q iteration \u2013 First experiences with a data efficient neural reinforcement learning method. In: Gama, J., Camacho, R., Brazdil, Pavel B., Jorge, A.M., Torgo, L. (eds.) ECML 2005. LNCS (LNAI), vol. 3720, pp. 317\u2013328. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11564096_32"},{"key":"63_CR9","unstructured":"Wang, Z., et al.: Dueling network architectures for deep reinforcement learning. In: ICML 2016 Proceedings of the 33rd International Conference on International Conference on Machine Learning, pp. 1993\u20132005. JMLR Press. New York (2016)"},{"key":"63_CR10","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. J. Comput. Sci. (2015)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"63_CR11","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. J. Nature 550, 354\u2013359 (2017)","journal-title":"J. Nature"},{"key":"63_CR12","doi-asserted-by":"crossref","unstructured":"Coppens, Y., Shirahata, K., Fukagai, T., Tomita, Y., Ike, A.: GUNREAL: GPU-accelerated UNsupervised REinforcement and Auxiliary Learning. In: Fifth International Symposium on Computing and Networking, pp. 330\u2013336, Shanghai (2017)","DOI":"10.1109\/CANDAR.2017.27"},{"key":"63_CR13","unstructured":"Babaeizadeh, M., Frosio, I., Tyree, S., Clemons, J., Kautz, J.: Reinforcement learning through asynchronous advantage actor-critic on a GPU. In: Fifth International Conference on Learning Representations, San Juan (2016)"},{"key":"63_CR14","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2015","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. MIT Press, Cambridge (2015)"},{"key":"63_CR15","volume-title":"The Principle of Reinforcement Learning and Its Application","author":"X Wang","year":"2014","unstructured":"Wang, X., Zhu, M., Cheng, Y.: The Principle of Reinforcement Learning and Its Application. Science Press, Beijing (2014)"},{"key":"63_CR16","doi-asserted-by":"publisher","DOI":"10.1002\/9781118884614","volume-title":"Multi-agent Machine Learning: A Reinforcement Approach, 458 p","author":"HM Schwartz","year":"2014","unstructured":"Schwartz, H.M.: Multi-agent Machine Learning: A Reinforcement Approach, 458 p. Wiley, US (2014)"},{"key":"63_CR17","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: The 31st International Conference on Machine Learning (ICML 2014), pp. 387\u2013395, Beijing (2014)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-04179-3_63","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T15:32:59Z","timestamp":1709825579000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-04179-3_63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030041786","9783030041793"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-04179-3_63","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"18 November 2018","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":"Siem Reap","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambodia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/iconip\/","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":"575","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":"401","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":"70% - 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":"4","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":"6","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)"}}]}}