{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T04:52:59Z","timestamp":1749099179002,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030893699"},{"type":"electronic","value":"9783030893705"}],"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\/978-3-030-89370-5_7","type":"book-chapter","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T01:02:59Z","timestamp":1635728579000},"page":"83-94","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["KG-RL: A Knowledge-Guided Reinforcement Learning for Massive Battle 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":"Xianya","family":"Mi","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":[[2021,11,1]]},"reference":[{"key":"7_CR1","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":"7_CR2","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, C., Yao, L., Wang, X., Zhang, W., et al.: Knowledge-guided deep reinforcement learning for interactive recommendation. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2020)","DOI":"10.1109\/IJCNN48605.2020.9207010"},{"issue":"7847","key":"7_CR3","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1038\/s41586-020-03157-9","volume":"590","author":"A Ecoffet","year":"2021","unstructured":"Ecoffet, A., Huizinga, J., Lehman, J., Stanley, K.O., Clune, J.: First return, then explore. Nature 590(7847), 580\u2013586 (2021)","journal-title":"Nature"},{"key":"7_CR4","unstructured":"Elo, A.E.: The rating of chessplayers, past and present. Arco Pub. (1978)"},{"key":"7_CR5","doi-asserted-by":"publisher","unstructured":"Han, X., Tang, H., Li, Y., Kou, G., Liu, L.: Improving multi-agent reinforcement learning with imperfect human knowledge. In: International Conference on Artificial Neural Networks, pp. 369\u2013380. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-61616-8_30","DOI":"10.1007\/978-3-030-61616-8_30"},{"key":"7_CR6","unstructured":"Hernandez-Leal, P., Kartal, B., Taylor, M.E.: A survey and critique of multiagent deep reinforcement learning"},{"key":"7_CR7","unstructured":"Jaderberg, M., Czarnecki, W., Dunning, I., Marris, L., Lever, G., Castaneda, A., et al.: Human-level performance in first-person multiplayer games with population-based deep reinforcement learning. arXiv:1807.01281 (2018)"},{"key":"7_CR8","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.artint.2016.07.004","volume":"241","author":"M Leonetti","year":"2016","unstructured":"Leonetti, M., Iocchi, L., Stone, P.: A synthesis of automated planning and reinforcement learning for efficient, robust decision-making. Artif. Intell. 241, 103\u2013130 (2016)","journal-title":"Artif. Intell."},{"key":"7_CR9","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv:1509.02971 (2015)"},{"key":"7_CR10","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, W., Hu, Y., Hao, J., Chen, X., Gao, Y.: Multi-agent game abstraction via graph attention neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7211\u20137218 (2020)","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"7_CR11","unstructured":"Long, Q., Zhou, Z., Gupta, A., Fang, F., Wu, Y., Wang, X.: Evolutionary population curriculum for scaling multi-agent reinforcement learning. arXiv:2003.10423 (2020)"},{"key":"7_CR12","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. NIPS (2017)"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Mao, H., et al.: Neighborhood cognition consistent multi-agent reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 7219\u20137226 (2020)","DOI":"10.1609\/aaai.v34i05.6212"},{"key":"7_CR14","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"key":"7_CR15","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: Qmix: monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4295\u20134304. PMLR (2018)"},{"key":"7_CR16","unstructured":"Silva, A., Gombolay, M.: Neural-encoding human experts\u2019 domain knowledge to warm start reinforcement learning. arXiv:1902.06007 (2019)"},{"key":"7_CR17","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":"7_CR18","unstructured":"Tang, Z., et al.: Discovering diverse multi-agent strategic behavior via reward randomization. arXiv:2103.04564 (2021)"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Wang, P., Fan, Y., Xia, L., Zhao, W.X., Niu, S., Huang, J.: Kerl: a knowledge-guided reinforcement learning model for sequential recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 209\u2013218 (2020)","DOI":"10.1145\/3397271.3401134"},{"key":"7_CR20","unstructured":"Xie, L., et al.: Learning with stochastic guidance for navigation. arXiv:1811.10756 (2018)"},{"key":"7_CR21","unstructured":"Yang, Y., Rui, L., Li, M., Ming, Z., Wang, J.: Mean field multi-agent reinforcement learning (2018)"},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Zheng, L., et al.: Magent: A many-agent reinforcement learning platform for artificial collective intelligence. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"7_CR23","unstructured":"Zhou, M., Liu, Z., Sui, P., Li, Y., Chung, Y.Y.: Learning implicit credit assignment for cooperative multi-agent reinforcement learning (2020)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2021: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89370-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,14]],"date-time":"2023-01-14T06:46:08Z","timestamp":1673678768000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89370-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030893699","9783030893705"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89370-5_7","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":"1 November 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2021","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"382","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":"93","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":"28","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":"24% - 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)"}}]}}