{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T10:30:58Z","timestamp":1760524258447,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863791"},{"type":"electronic","value":"9783030863807"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86380-7_51","type":"book-chapter","created":{"date-parts":[[2021,9,10]],"date-time":"2021-09-10T12:03:14Z","timestamp":1631275394000},"page":"625-637","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Independent Deep Deterministic Policy Gradient Reinforcement Learning in Cooperative Multiagent Pursuit Games"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1894-3678","authenticated-orcid":false,"given":"Shiyang","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7127-2300","authenticated-orcid":false,"given":"Weiya","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoguang","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,7]]},"reference":[{"key":"51_CR1","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: CVPR (July 2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"51_CR2","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator. In: Proceedings of the 1st Annual Conference on Robot Learning, pp. 1\u201316 (2017)"},{"key":"51_CR3","unstructured":"Hao, X., Wang, W., Hao, J., Yang, Y.: Independent generative adversarial self-imitation learning in cooperative multiagent systems. arXiv preprint arXiv:1909.11468 (2019)"},{"key":"51_CR4","doi-asserted-by":"crossref","unstructured":"Harutyunyan, A., Devlin, S., Vrancx, P., Now\u00e9, A.: Expressing arbitrary reward functions as potential-based advice. In: AAAI, pp. 2652\u20132658 (2015)","DOI":"10.1609\/aaai.v29i1.9628"},{"issue":"6","key":"51_CR5","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1007\/s10458-019-09421-1","volume":"33","author":"P Hernandez-Leal","year":"2019","unstructured":"Hernandez-Leal, P., Kartal, B., Taylor, M.E.: A survey and critique of multiagent deep reinforcement learning. Auton. Agents Multi-agent Syst. 33(6), 750\u2013797 (2019). https:\/\/doi.org\/10.1007\/s10458-019-09421-1","journal-title":"Auton. Agents Multi-agent Syst."},{"key":"51_CR6","unstructured":"Jaques, N., et al.: Social influence as intrinsic motivation for multi-agent deep reinforcement learning. In: ICML, pp. 3040\u20133049. PMLR (2019)"},{"key":"51_CR7","unstructured":"Jiang, J., Lu, Z.: Learning attentional communication for multi-agent cooperation. CoRR abs\/1805.07733 (2018). http:\/\/arxiv.org\/abs\/1805.07733"},{"key":"51_CR8","doi-asserted-by":"crossref","unstructured":"LaValle, S.M.: Planning Algorithms. Cambridge University Press (2006)","DOI":"10.1017\/CBO9780511546877"},{"key":"51_CR9","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"51_CR10","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: NIPS (2017)"},{"key":"51_CR11","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: ICML, vol. 99, pp. 278\u2013287 (1999)"},{"key":"51_CR12","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 16\u201317 (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"51_CR13","unstructured":"Peng, P., et al.: Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft Combat Games. arXiv preprint arXiv:1703.10069 (2017)"},{"issue":"02","key":"51_CR14","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1142\/S2301385018400022","volume":"6","author":"M Radmanesh","year":"2018","unstructured":"Radmanesh, M., Kumar, M., Guentert, P.H., Sarim, M.: Overview of path-planning and obstacle avoidance algorithms for UAVs: a comparative study. Unmanned Syst. 6(02), 95\u2013118 (2018)","journal-title":"Unmanned Syst."},{"key":"51_CR15","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"key":"51_CR16","unstructured":"Siddiqui, R.: Path planning using potential field algorithm. Medium (July 2018)"},{"key":"51_CR17","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic Policy Gradient Algorithms (2014)"},{"key":"51_CR18","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"51_CR19","unstructured":"Xie, L., et al.: Learning with Stochastic guidance for navigation. arXiv preprint arXiv:1811.10756 (2018)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86380-7_51","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,8]],"date-time":"2023-01-08T23:44:09Z","timestamp":1673221449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86380-7_51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863791","9783030863807"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86380-7_51","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"7 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2021\/","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":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"496","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":"265","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":"4","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":"53% - 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":"2.5","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)"}},{"value":"Conference was held online due to the COVID-19 pandemic.","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)"}}]}}