{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:01:17Z","timestamp":1743022877608,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819755806"},{"type":"electronic","value":"9789819755813"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-97-5581-3_36","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T19:02:53Z","timestamp":1722538973000},"page":"443-454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OB-HPPO: An Option and Intrinsic Curiosity Based Hierarchical Reinforcement Learning Approach for Real-Time Strategy Games"],"prefix":"10.1007","author":[{"given":"Ruilin","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Yanlong","family":"Zhai","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"You","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yanglin","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"issue":"1\u20132","key":"36_CR1","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPS and semi-MDPS: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1\u20132), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Churchill, D., Saffidine, A., Buro, M.: Fast heuristic search for RTS game combat scenarios. In: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, vol. 8, no. 1, pp. 112\u2013117 (2012)","DOI":"10.1609\/aiide.v8i1.12527"},{"key":"36_CR3","unstructured":"Z, Z.-Z., Dou, X., Liu, T.-Y.: Question and answer system based on military knowledge graph. In: Proceedings of the 6th China Command and Control Congress, vol. 1 (2018)"},{"issue":"4","key":"36_CR4","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1109\/TG.2018.2848913","volume":"11","author":"C Silva","year":"2018","unstructured":"Silva, C., Moraes, R.O., Lelis, L.H., Gal, K.: Strategy generation for multiunit real-time games via voting. IEEE Trans. Games 11(4), 426\u2013435 (2018)","journal-title":"IEEE Trans. Games"},{"key":"36_CR5","doi-asserted-by":"crossref","unstructured":"Barriga, N., Stanescu, M., Buro, M.: Puppet search: enhancing scripted behavior by look-ahead search with applications to real-time strategy games. In: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, vol. 11, no. 1, pp. 9\u201315 (2015)","DOI":"10.1609\/aiide.v11i1.12779"},{"key":"36_CR6","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, Part IV. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"36_CR7","unstructured":"Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)"},{"issue":"8","key":"36_CR8","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"7676","key":"36_CR9","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"issue":"7782","key":"36_CR10","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"},{"key":"36_CR11","unstructured":"Berner, C., et al.: Dota 2 with large scale deep reinforcement learning, arXiv preprint arXiv:1912.06680 (2019)"},{"key":"36_CR12","unstructured":"Vinyals, O., et al.: Starcraft II: a new challenge for reinforcement learning, arXiv preprint arXiv:1708.04782 (2017)"},{"key":"36_CR13","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge, arXiv preprint arXiv:1902.04043 (2019)"},{"key":"36_CR14","unstructured":"Qiu, W., et al.: Off-beat multi-agent reinforcement learning, arXiv preprint arXiv:2205.13718 (2022)"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Song, H., Feng, M., Zhou, W., Li, H.: MA2CL: masked attentive contrastive learning for multi-agent reinforcement learning, arXiv preprint arXiv:2306.02006 (2023)","DOI":"10.24963\/ijcai.2023\/470"},{"key":"36_CR16","doi-asserted-by":"crossref","unstructured":"Tang, X., Yu, H.: Competitive-cooperative multi-agent reinforcement learning for auction-based federated learning. In: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pp. 4262\u20134270 (2023)","DOI":"10.24963\/ijcai.2023\/474"},{"key":"36_CR17","unstructured":"Li, L.: Research on hierarchical reinforcement learning method based on option automatic generation (2009)"},{"key":"36_CR18","unstructured":"Lee, S., Kim, J., Jang, I., Kim, H.J.: DHRL: a graph-based approach for Longhorizon and sparse hierarchical reinforcement learning. Adv. Neural Inf. Process. Syst. 35, 13668\u201313678 (2022)"},{"key":"36_CR19","unstructured":"Chauhan, K., Chatterjee, S., Reddy, A., Ravindran, B., Shenoy, P.: Matching options to tasks using option-indexed hierarchical reinforcement learning, arXiv preprint arXiv:2206.05750 (2022)"},{"key":"36_CR20","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/3-540-36755-1_25","volume-title":"Machine Learning: ECML 2002","author":"I Menache","year":"2002","unstructured":"Menache, I., Mannor, S., Shimkin, N.: Q-cut\u2014dynamic discovery of sub-goals in reinforcement learning. In: Elomaa, T., Mannila, H., Toivonen, H. (eds.) ECML 2002. LNCS (LNAI), vol. 2430, pp. 295\u2013306. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-36755-1_25"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5581-3_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T19:19:35Z","timestamp":1722539975000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5581-3_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819755806","9789819755813"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5581-3_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}