{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T21:56:12Z","timestamp":1768082172452,"version":"3.49.0"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030616151","type":"print"},{"value":"9783030616168","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\/978-3-030-61616-8_30","type":"book-chapter","created":{"date-parts":[[2020,10,16]],"date-time":"2020-10-16T23:07:42Z","timestamp":1602889662000},"page":"369-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improving Multi-agent Reinforcement Learning with Imperfect Human Knowledge"],"prefix":"10.1007","author":[{"given":"Xiaoxu","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyao","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang","family":"Kou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leilei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,14]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Ammanabrolu, P., Riedl, M.O.: Playing text-adventure games with graph-based deep reinforcement learning. arXiv preprint arXiv:1812.01628 (2018)","DOI":"10.18653\/v1\/N19-1358"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Bougie, N., Ichise, R.: Deep reinforcement learning boosted by external knowledge. In: Proceedings of the 33rd Annual ACM Symposium on Applied Computing, pp. 331\u2013338 (2018)","DOI":"10.1145\/3167132.3167165"},{"key":"30_CR3","unstructured":"Bougie12, N., Ichise, R.: Rule-based reinforcement learning augmented by external knowledge"},{"key":"30_CR4","unstructured":"Du, Y., Narasimhan, K.: Task-agnostic dynamics priors for deep reinforcement learning. arXiv preprint arXiv:1905.04819 (2019)"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Hester, T., Vecerik, M., et al.: Deep q-learning from demonstrations. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"30_CR6","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Advances in Neural Information Processing Systems, pp. 4565\u20134573 (2016)"},{"key":"30_CR7","unstructured":"Moreno, D.L., Regueiro, C.V., et al.: Using prior knowledge to improve reinforcement learning in mobile robotics. In: Proceedings of the Towards Autonomous Robotics Systems, University of Essex, UK (2004)"},{"key":"30_CR8","unstructured":"Rashid, T., Samvelyan, M., et al.: QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, pp. 4292\u20134301 (2018)"},{"key":"30_CR9","unstructured":"Sunehag, P., Lever, G., 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":"30_CR10","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: Independent vs. cooperative agents. In: Proceedings of the Tenth International Conference on Machine Learning, pp. 330\u2013337 (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Wang, Z., Taylor, M.E.: Interactive reinforcement learning with dynamic reuse of prior knowledge from human and agent demonstrations. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, pp. 3820\u20133827. ijcai.org (2019)","DOI":"10.24963\/ijcai.2019\/530"},{"key":"30_CR12","doi-asserted-by":"publisher","first-page":"109301","DOI":"10.1109\/ACCESS.2019.2933454","volume":"7","author":"G Zhang","year":"2019","unstructured":"Zhang, G., Li, Y., et al.: Efficient training techniques for multi-agent reinforcement learning in combat tasks. IEEE Access 7, 109301\u2013109310 (2019)","journal-title":"IEEE Access"},{"key":"30_CR13","unstructured":"Zhang, H., Gao, Z., et al.: Faster and safer training by embedding high-level knowledge into deep reinforcement learning. arXiv preprint arXiv:1910.09986 (2019)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-61616-8_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T18:27:59Z","timestamp":1669228079000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-61616-8_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030616151","9783030616168"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-61616-8_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"14 October 2020","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2020\/","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":"249","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":"139","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":"56% - 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":"*The conference was postponed to 2021 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)"}}]}}