{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T18:14:39Z","timestamp":1771697679461,"version":"3.50.1"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030946616","type":"print"},{"value":"9783030946623","type":"electronic"}],"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\/978-3-030-94662-3_3","type":"book-chapter","created":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T12:03:08Z","timestamp":1641902588000},"page":"38-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["SEIHAI: A Sample-Efficient Hierarchical AI for\u00a0the\u00a0MineRL Competition"],"prefix":"10.1007","author":[{"given":"Hangyu","family":"Mao","sequence":"first","affiliation":[]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiaotian","family":"Hao","sequence":"additional","affiliation":[]},{"given":"Yihuan","family":"Mao","sequence":"additional","affiliation":[]},{"given":"Yiming","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Chengjie","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Pingzhong","family":"Tang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,11]]},"reference":[{"key":"3_CR1","unstructured":"Amiranashvili, A., Dorka, N., Burgard, W., Koltun, V., Brox, T.: Scaling imitation learning in minecraft. arXiv preprint arXiv:2007.02701 (2020)"},{"issue":"2","key":"3_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1667053.1667056","volume":"57","author":"DM Blei","year":"2010","unstructured":"Blei, D.M., Griffiths, T.L., Jordan, M.I.: The nested Chinese restaurant process and Bayesian nonparametric inference of topic hierarchies. J. ACM (JACM) 57(2), 1\u201330 (2010)","journal-title":"J. ACM (JACM)"},{"key":"3_CR3","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-policy deep reinforcement learning without exploration. In: International Conference on Machine Learning, pp. 2052\u20132062. PMLR (2019)"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 3389\u20133396. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"3_CR5","unstructured":"Guss, W.H., et al.: The MineRL 2020 competition on sample efficient reinforcement learning using human priors. arXiv preprint arXiv:2101.11071 (2021)"},{"key":"3_CR6","unstructured":"Guss, W.H., et al.: NeurIPS 2019 competition: the MineRL competition on sample efficient reinforcement learning using human priors. arXiv preprint arXiv:1904.10079 (2019)"},{"key":"3_CR7","unstructured":"Guss, W.H., et al.: The MineRL competition on sample efficient reinforcement learning using human priors. arXiv e-prints (2019)"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Guss, W.H., et al.: MineRL: a large-scale dataset of minecraft demonstrations. arXiv preprint arXiv:1907.13440 (2019)","DOI":"10.24963\/ijcai.2019\/339"},{"key":"3_CR9","unstructured":"Guss, W.H., et al.: Towards robust and domain agnostic reinforcement learning competitions: MineRL 2020. In: NeurIPS 2020 Competition and Demonstration Track, pp. 233\u2013252. PMLR (2021)"},{"key":"3_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Hester, T., et al.: Deep Q-learning from demonstrations. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"3_CR12","first-page":"4565","volume":"29","author":"J Ho","year":"2016","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. Adv. Neural Inf. Process. Syst. 29, 4565\u20134573 (2016)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3_CR13","unstructured":"Kang, B., Jie, Z., Feng, J.: Policy optimization with demonstrations. In: International Conference on Machine Learning, pp. 2469\u20132478. PMLR (2018)"},{"key":"3_CR14","unstructured":"Kumar, A., Fu, J., Tucker, G., Levine, S.: Stabilizing off-policy Q-learning via bootstrapping error reduction. arXiv preprint arXiv:1906.00949 (2019)"},{"key":"3_CR15","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative Q-learning for offline reinforcement learning. arXiv preprint arXiv:2006.04779 (2020)"},{"issue":"2","key":"3_CR16","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/S0031-3203(02)00060-2","volume":"36","author":"A Likas","year":"2003","unstructured":"Likas, A., Vlassis, N., Verbeek, J.J.: The global k-means clustering algorithm. Pattern Recogn. 36(2), 451\u2013461 (2003)","journal-title":"Pattern Recogn."},{"key":"3_CR17","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: ICLR (2016)"},{"issue":"2","key":"3_CR18","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theor. 28(2), 129\u2013137 (1982)","journal-title":"IEEE Trans. Inf. Theor."},{"key":"3_CR19","unstructured":"MacQueen, J., et al.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, vol. 1, pp. 281\u2013297. Oakland, CA, USA (1967)"},{"key":"3_CR20","unstructured":"Mao, H., Gong, Z., Ni, Y., Xiao, Z.: ACCNet: actor-coordinator-critic net for \u201clearning-to-communicate\u201d with deep multi-agent reinforcement learning. arXiv preprint arXiv:1706.03235 (2017)"},{"key":"3_CR21","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":"3_CR22","unstructured":"Mao, H., Zhang, Z., Xiao, Z., Gong, Z.: Modelling the dynamic joint policy of teammates with attention multi-agent DDPG. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (2019)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Mao, H., Zhang, Z., Xiao, Z., Gong, Z., Ni, Y.: Learning agent communication under limited bandwidth by message pruning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5142\u20135149 (2020)","DOI":"10.1609\/aaai.v34i04.5957"},{"issue":"1","key":"3_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-020-09455-w","volume":"34","author":"H Mao","year":"2020","unstructured":"Mao, H., Zhang, Z., Xiao, Z., Gong, Z., Ni, Y.: Learning multi-agent communication with double attentional deep reinforcement learning. Auton. Agents Multi Agent Syst. 34(1), 1\u201334 (2020). https:\/\/doi.org\/10.1007\/s10458-020-09455-w","journal-title":"Auton. Agents Multi Agent Syst."},{"key":"3_CR25","unstructured":"Milani, S., et al.: Retrospective analysis of the 2019 MineRL competition on sample efficient reinforcement learning. In: NeurIPS 2019 Competition and Demonstration Track, pp. 203\u2013214. PMLR (2020)"},{"issue":"7540","key":"3_CR26","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"1\u20132","key":"3_CR27","first-page":"1","volume":"7","author":"T Osa","year":"2018","unstructured":"Osa, T., Pajarinen, J., Neumann, G., Bagnell, J.A., Abbeel, P., Peters, J., et al.: An algorithmic perspective on imitation learning. Found. Trends Rob. 7(1\u20132), 1\u2013179 (2018)","journal-title":"Found. Trends Rob."},{"key":"3_CR28","unstructured":"Reddy, S., Dragan, A.D., Levine, S.: SQIL: imitation learning via reinforcement learning with sparse rewards. In: ICLR (2019)"},{"key":"3_CR29","unstructured":"Scheller, C., Schraner, Y., Vogel, M.: Sample efficient reinforcement learning through learning from demonstrations in minecraft. In: NeurIPS 2019 Competition and Demonstration Track, pp. 67\u201376. PMLR (2020)"},{"key":"3_CR30","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: ICML, pp. 387\u2013395. PMLR (2014)"},{"key":"3_CR31","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.cogsys.2020.08.012","volume":"65","author":"A Skrynnik","year":"2021","unstructured":"Skrynnik, A., Staroverov, A., Aitygulov, E., Aksenov, K., Davydov, V., Panov, A.I.: Hierarchical deep q-network from imperfect demonstrations in minecraft. Cogn. Syst. Res. 65, 74\u201378 (2021)","journal-title":"Cogn. Syst. Res."},{"key":"3_CR32","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"3_CR33","unstructured":"Vecerik, M., et al.: Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards. arXiv preprint arXiv:1707.08817 (2017)"}],"container-title":["Lecture Notes in Computer Science","Distributed Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-94662-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T15:20:58Z","timestamp":1674400858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-94662-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030946616","9783030946623"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-94662-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Distributed Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dai22021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.adai.ai\/dai\/2021\/2021.html","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":"31","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":"15","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":"48% - 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":"4","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)"}}]}}