{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:14:37Z","timestamp":1771697677687,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030638221","type":"print"},{"value":"9783030638238","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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":[[2020]]},"DOI":"10.1007\/978-3-030-63823-8_46","type":"book-chapter","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T16:09:10Z","timestamp":1605715750000},"page":"395-402","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Investigating Partner Diversification Methods in Cooperative Multi-agent Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Rujikorn","family":"Charakorn","sequence":"first","affiliation":[]},{"given":"Poramate","family":"Manoonpong","sequence":"additional","affiliation":[]},{"given":"Nat","family":"Dilokthanakul","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,17]]},"reference":[{"key":"46_CR1","unstructured":"Bansal, T., Pachocki, J., Sidor, S., Sutskever, I., Mordatch, I.: Emergent complexity via multi-agent competition. arXiv preprint arXiv:1710.03748 (2017)"},{"key":"46_CR2","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.artint.2016.10.005","volume":"242","author":"S Barrett","year":"2017","unstructured":"Barrett, S., Rosenfeld, A., Kraus, S., Stone, P.: Making friends on the fly: cooperating with new teammates. Artif. Intell. 242, 132\u2013171 (2017)","journal-title":"Artif. Intell."},{"key":"46_CR3","doi-asserted-by":"crossref","unstructured":"Canaan, R., Gao, X., Togelius, J., Nealen, A., Menzel, S.: Generating and adapting to diverse ad-hoc cooperation agents in Hanabi. arXiv preprint arXiv:2004.13710(2020)","DOI":"10.1109\/CIG.2019.8847944"},{"key":"46_CR4","unstructured":"Carroll, M., et al.: On the utility of learning about humans for human-AI coordination. In: Advances in Neural Information Processing Systems, pp. 5175\u20135186 (2019)"},{"key":"46_CR5","doi-asserted-by":"crossref","unstructured":"Foerster, J.N., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"46_CR6","unstructured":"Ghosh, A., Tschiatschek, S., Mahdavi, H., Singla, A.: Towards deployment of robust AI agents for human-machine partnerships. arXiv preprint arXiv:1910.02330 (2019)"},{"key":"46_CR7","unstructured":"Grover, A., Al-Shedivat, M., Gupta, J.K., Burda, Y., Edwards, H.: Learning policy representations in multiagent systems. arXiv preprint arXiv:1806.06464 (2018)"},{"key":"46_CR8","doi-asserted-by":"crossref","unstructured":"Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"46_CR9","unstructured":"Hu, H., Foerster, J.N.: Simplified action decoder for deep multi-agent reinforcement learning. arXiv preprint arXiv:1912.02288 (2019)"},{"key":"46_CR10","unstructured":"Hu, H., Lerer, A., Peysakhovich, A., Foerster, J.: \u201cOther-play\u201d for zero-shot coordination. arXiv preprint arXiv:2003.02979 (2020)"},{"key":"46_CR11","unstructured":"Islam, R., Henderson, P., Gomrokchi, M., Precup, D.: Reproducibility of benchmarked deep reinforcement learning tasks for continuous control. arXiv preprintarXiv:1708.04133 (2017)"},{"key":"46_CR12","unstructured":"Justesen, N., Torrado, R.R., Bontrager, P., Khalifa, A., Togelius, J., Risi, S.: Illuminating generalization in deep reinforcement learning through procedural level generation. arXiv preprint arXiv:1806.10729 (2018)"},{"key":"46_CR13","unstructured":"Lanctot, M., et al.: A unified game-theoretic approach to multiagent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 4190\u20134203 (2017)"},{"key":"46_CR14","unstructured":"Le, H.M., Yue, Y., Carr, P., Lucey, P.: Coordinated multi-agent imitation learning. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 1995\u20132003. JMLR. org (2017)"},{"key":"46_CR15","doi-asserted-by":"crossref","unstructured":"Li, M.G., Jiang, B., Zhu, H., Che, Z., Liu, Y.: Generative attention networks for multi-agent behavioral modeling. In: AAAI, pp. 7195\u20137202 (2020)","DOI":"10.1609\/aaai.v34i05.6209"},{"key":"46_CR16","unstructured":"Liu, S., Lever, G., Merel, J., Tunyasuvunakool, S., Heess, N., Graepel, T.: Emergent coordination through competition. arXiv preprint arXiv:1902.07151 (2019)"},{"key":"46_CR17","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, pp. 6379\u20136390 (2017)"},{"key":"46_CR18","unstructured":"OpenAI, Berner, C., et al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)"},{"key":"46_CR19","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"46_CR20","doi-asserted-by":"crossref","unstructured":"Stone, P., Kaminka, G.A., Kraus, S., Rosenschein, J.S.: Ad hoc autonomous agent teams: Collaboration without pre-coordination. In: Twenty-Fourth AAAI Conference on Artificial Intelligence (2010)","DOI":"10.1609\/aaai.v24i1.7529"},{"issue":"7782","key":"46_CR21","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"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63823-8_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T17:21:39Z","timestamp":1669656099000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63823-8_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030638221","9783030638238"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63823-8_46","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"17 November 2020","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":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apnns.org\/ICONIP2020","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":"618","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":"187","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":"189","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":"30% - 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":"3.18","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":"3.68","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)"}},{"value":"Due to COVID-19 pandemic the conference was held virtually.","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)"}}]}}