{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T14:28:04Z","timestamp":1758810484832,"version":"3.40.3"},"publisher-location":"Cham","reference-count":12,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031138218"},{"type":"electronic","value":"9783031138225"}],"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\/978-3-031-13822-5_8","type":"book-chapter","created":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T18:18:24Z","timestamp":1659550704000},"page":"77-87","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-robot Cooperation Learning Based on\u00a0Powell Deep Deterministic Policy Gradient"],"prefix":"10.1007","author":[{"given":"Zongyuan","family":"Li","sequence":"first","affiliation":[]},{"given":"Chuxi","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Ziyi","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xian","family":"Guo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,8,4]]},"reference":[{"unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv e-prints arXiv:1312.5602, December 2013","key":"8_CR1"},{"doi-asserted-by":"crossref","unstructured":"van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. arXiv e-prints arXiv:1509.06461, September 2015","key":"8_CR2","DOI":"10.1609\/aaai.v30i1.10295"},{"unstructured":"Wang, Z., Schaul, T., Hessel, M., van Hasselt, H., Lanctot, M., de Freitas, N.: Dueling network architectures for deep reinforcement learning. arXiv e-prints arXiv:1511.06581, November 2015","key":"8_CR3"},{"issue":"3\u20134","key":"8_CR4","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv e-prints arXiv:1509.02971, September 2015","key":"8_CR5"},{"unstructured":"Schulman, J., Levine, S., Moritz, P., Jordan, M.I., Abbeel, P.: Trust region policy optimization. arXiv e-prints arXiv:1502.05477, February 2015","key":"8_CR6"},{"unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv e-prints arXiv:1707.06347, July 2017","key":"8_CR7"},{"unstructured":"Tampuu, A., et al.: Multiagent cooperation and competition with deep reinforcement learning. arXiv e-prints arXiv:1511.08779, November 2015","key":"8_CR8"},{"doi-asserted-by":"crossref","unstructured":"Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. arXiv e-prints arXiv:1705.08926, May 2017","key":"8_CR9","DOI":"10.1609\/aaai.v32i1.11794"},{"unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. arXiv e-prints arXiv:1706.02275, June 2017","key":"8_CR10"},{"unstructured":"Sunehag, P., et al.: Value-decomposition networks for cooperative multi-agent learning. arXiv e-prints arXiv:1706.05296, June 2017","key":"8_CR11"},{"unstructured":"Rashid, T., Samvelyan, M., Schroeder de Witt, C., Farquhar, G., Foerster, J., Whiteson, S.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. arXiv e-prints arXiv:1803.11485, March 2018","key":"8_CR12"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-13822-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T23:08:46Z","timestamp":1660604926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-13822-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031138218","9783031138225"],"references-count":12,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-13822-5_8","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":"4 August 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Harbin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"1 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icira2022.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"442","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":"284","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":"64% - 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","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":"5","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)"}}]}}