{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T03:10:05Z","timestamp":1743995405992,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031877681","type":"print"},{"value":"9783031877698","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-87769-8_23","type":"book-chapter","created":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T02:36:59Z","timestamp":1743993419000},"page":"260-270","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Collaborative Warehouse Order Fulfillment via\u00a0Goal-Directed Curiosity and\u00a0Hierarchical Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Maram","family":"Hasan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajdeep","family":"Niyogi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,8]]},"reference":[{"key":"23_CR1","unstructured":"Ahilan, S., Dayan, P.: Feudal multi-agent hierarchies for cooperative reinforcement learning. arXiv preprint arXiv:1901.08492 (2019)"},{"key":"23_CR2","unstructured":"Bartholdi, J., Hackman, S.: Warehouse & distribution science (release 0.98. 1) (2019). https:\/\/www.warehouse-science.com\/book\/editions\/wh-sci-0.98.1.pdf"},{"key":"23_CR3","unstructured":"Christianos, F., Sch\u00e4fer, L., Albrecht, S.V.: Shared experience actor-critic for multi-agent reinforcement learning. arXiv preprint arXiv:2006.07169 (2020)"},{"issue":"103","key":"23_CR4","first-page":"729","volume":"137","author":"\u00cdR da Costa Barros","year":"2021","unstructured":"da Costa Barros, \u00cd.R., Nascimento, T.P.: Robotic mobile fulfillment systems: a survey on recent developments and research opportunities. Robot. Auton. Syst. 137(103), 729 (2021)","journal-title":"Robot. Auton. Syst."},{"issue":"4","key":"23_CR5","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1109\/TASE.2012.2214676","volume":"9","author":"R D\u2019Andrea","year":"2012","unstructured":"D\u2019Andrea, R.: Guest editorial: a revolution in the warehouse: a retrospective on kiva systems and the grand challenges ahead. IEEE Trans. Autom. Sci. Eng. 9(4), 638\u2013639 (2012)","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"23_CR6","unstructured":"Krnjaic, A., Thomas, J.D., Papoudakis, G., Sch\u00e4fer, L., B\u00f6rsting, P., Albrecht, S.V.: Scalable multi-agent reinforcement learning for warehouse logistics with robotic and human co-workers. arXiv preprint arXiv:2212.11498 (2022)"},{"key":"23_CR7","first-page":"3675","volume":"29","author":"TD Kulkarni","year":"2016","unstructured":"Kulkarni, T.D., Narasimhan, K., Saeedi, A., Tenenbaum, J.: Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. Adv. Neural. Inf. Process. Syst. 29, 3675\u20133683 (2016)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR8","doi-asserted-by":"publisher","first-page":"49089","DOI":"10.1109\/ACCESS.2018.2854283","volume":"6","author":"TP Le","year":"2018","unstructured":"Le, T.P., Vien, N.A., Chung, T.: A deep hierarchical reinforcement learning algorithm in partially observable Markov decision processes. IEEE Access 6, 49089\u201349102 (2018)","journal-title":"IEEE Access"},{"issue":"3","key":"23_CR9","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.3390\/app11031209","volume":"11","author":"H Lee","year":"2021","unstructured":"Lee, H., Jeong, J.: Mobile robot path optimization technique based on reinforcement learning algorithm in warehouse environment. Appl. Sci. 11(3), 1209 (2021)","journal-title":"Appl. Sci."},{"key":"23_CR10","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter\u00a0Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"23_CR11","unstructured":"Papoudakis, G., Christianos, F., Sch\u00e4fer, L., Albrecht, S.V.: Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks. arXiv preprint arXiv:2006.07869 (2020)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: International Conference on Machine Learning, pp. 2778\u20132787. PMLR (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"23_CR13","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)"},{"issue":"1\u20132","key":"23_CR14","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":"23_CR15","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":"23_CR16","unstructured":"Tang, H., et\u00a0al.: Hierarchical deep multiagent reinforcement learning with temporal abstraction. arXiv preprint arXiv:1809.09332(2018)"},{"key":"23_CR17","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/978-3-030-01370-7_19","volume-title":"Intelligent Autonomous Systems 15","author":"H Wang","year":"2019","unstructured":"Wang, H., Chen, W., Wang, J.: Heterogeneous multi-agent routing strategy for robot-and-picker-to-good order fulfillment system. In: Strand, M., Dillmann, R., Menegatti, E., Ghidoni, S. (eds.) IAS 2018. AISC, vol. 867, pp. 237\u2013249. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-01370-7_19"},{"issue":"11","key":"23_CR18","doi-asserted-by":"publisher","first-page":"5174","DOI":"10.1109\/TNNLS.2018.2805379","volume":"29","author":"Z Yang","year":"2018","unstructured":"Yang, Z., Merrick, K., Jin, L., Abbass, H.A.: Hierarchical deep reinforcement learning for continuous action control. IEEE Trans. Neural Netw. Learn. Syst. 29(11), 5174\u20135184 (2018)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"1","key":"23_CR19","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.ejor.2021.05.033","volume":"298","author":"I \u017dulj","year":"2022","unstructured":"\u017dulj, I., Salewski, H., Goeke, D., Schneider, M.: Order batching and batch sequencing in an amr-assisted picker-to-parts system. Eur. J. Oper. Res. 298(1), 182\u2013201 (2022)","journal-title":"Eur. J. Oper. Res."}],"container-title":["Lecture Notes on Data Engineering and Communications Technologies","Advanced Information Networking and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-87769-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T02:37:21Z","timestamp":1743993441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-87769-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031877681","9783031877698"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-87769-8_23","relation":{},"ISSN":["2367-4512","2367-4520"],"issn-type":[{"value":"2367-4512","type":"print"},{"value":"2367-4520","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"8 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AINA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Information Networking and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Barcelona","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"39","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aina0","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/voyager.ce.fit.ac.jp\/conf\/aina\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}