{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:55:26Z","timestamp":1778813726746,"version":"3.51.4"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031164736","type":"print"},{"value":"9783031164743","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\/978-3-031-16474-3_2","type":"book-chapter","created":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T14:16:28Z","timestamp":1662992188000},"page":"15-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Hierarchically Structured Scheduling and\u00a0Execution of\u00a0Tasks in\u00a0a\u00a0Multi-agent Environment"],"prefix":"10.1007","author":[{"given":"Diogo","family":"Carvalho","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Biswa","family":"Sengupta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,13]]},"reference":[{"key":"2_CR1","unstructured":"Ahilan, S., Dayan, P.: Feudal multi-agent hierarchies for cooperative reinforcement learning. arXiv preprint arXiv:1901.08492 (2019)"},{"key":"2_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/BFb0029569","volume-title":"Online Algorithms","author":"Y Azar","year":"1998","unstructured":"Azar, Y.: On-line load balancing. In: Fiat, A., Woeginger, G.J. (eds.) Online Algorithms. LNCS, vol. 1442, pp. 178\u2013195. Springer, Heidelberg (1998). https:\/\/doi.org\/10.1007\/BFb0029569"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bacon, P.L., Harb, J., Precup, D.: The option-critic architecture. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)","DOI":"10.1609\/aaai.v31i1.10916"},{"key":"2_CR4","unstructured":"Chevalier-Boisvert, M., Willems, L., Pal, S.: Minimalistic gridworld environment for openai gym (2018). https:\/\/github.com\/maximecb\/gym-minigrid"},{"key":"2_CR5","unstructured":"Christianos, F., Papoudakis, G., Rahman, M.A., Albrecht, S.V.: Scaling multi-agent reinforcement learning with selective parameter sharing. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, 18\u201324 July 2021, vol. 139, pp. 1989\u20131998. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/christianos21a.html"},{"key":"2_CR6","unstructured":"Claes, D., Oliehoek, F., Baier, H., Tuyls, K., et al.: Decentralised online planning for multi-robot warehouse commissioning. In: International Conference on Autonomous Agents and Multiagent Systems, pp. 492\u2013500 (2017)"},{"key":"2_CR7","unstructured":"Dayan, P., Hinton, G.E.: Feudal reinforcement learning. In: Hanson, S., Cowan, J., Giles, C. (eds.) Advances in Neural Information Processing Systems, vol. 5. Morgan-Kaufmann (1993)"},{"key":"2_CR8","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1613\/jair.639","volume":"13","author":"TG Dietterich","year":"2000","unstructured":"Dietterich, T.G.: Hierarchical reinforcement learning with the maxq value function decomposition. J. Artif. Intell. Res. 13, 227\u2013303 (2000)","journal-title":"J. Artif. Intell. Res."},{"key":"2_CR9","unstructured":"Fickinger, A.: Multi-agent gridworld environment for openai gym (2020). https:\/\/github.com\/ArnaudFickinger\/gym-multigrid"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Fluri, C., Ruch, C., Zilly, J., Hakenberg, J., Frazzoli, E.: Learning to operate a fleet of cars. In: IEEE Intelligent Transportation Systems Conference (ITSC) (2019)","DOI":"10.1109\/ITSC.2019.8917533"},{"key":"2_CR11","unstructured":"Foerster, J., Assael, I.A., de Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29. Curran Associates, Inc. (2016)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Gammelli, D., Yang, K., Harrison, J., Rodrigues, F., Pereira, F.C., Pavone, M.: Graph neural network reinforcement learning for autonomous mobility-on-demand systems. arXiv preprint arXiv:2104.11434 (2021)","DOI":"10.1109\/CDC45484.2021.9683135"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Gu\u00e9riau, M., Dusparic, I.: Samod: Shared autonomous mobility-on-demand using decentralized reinforcement learning. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC). IEEE (2018)","DOI":"10.1109\/ITSC.2018.8569608"},{"key":"2_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","volume-title":"Autonomous Agents and Multiagent Systems","author":"JK Gupta","year":"2017","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: Sukthankar, G., Rodriguez-Aguilar, J.A. (eds.) AAMAS 2017. LNCS (LNAI), vol. 10642, pp. 66\u201383. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-71682-4_5"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Holler, J., et al.: Deep reinforcement learning for multi-driver vehicle dispatching and repositioning problem. In: 2019 IEEE International Conference on Data Mining (ICDM), pp. 1090\u20131095. IEEE (2019)","DOI":"10.1109\/ICDM.2019.00129"},{"key":"2_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106244","volume":"204","author":"Y Hu","year":"2020","unstructured":"Hu, Y., Yao, Y., Lee, W.S.: A reinforcement learning approach for optimizing multiple traveling salesman problems over graphs. Knowl.-Based Syst. 204, 106244 (2020)","journal-title":"Knowl.-Based Syst."},{"key":"2_CR17","unstructured":"Kaempfer, Y., Wolf, L.: Learning the multiple traveling salesmen problem with permutation invariant pooling networks. arXiv preprint arXiv:1803.09621 (2018)"},{"key":"2_CR18","unstructured":"Kong, X., Xin, B., Liu, F., Wang, Y.: Revisiting the master-slave architecture in multi-agent deep reinforcement learning. arXiv preprint arXiv:1712.07305 (2017)"},{"key":"2_CR19","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.neucom.2016.01.031","volume":"190","author":"L Kraemer","year":"2016","unstructured":"Kraemer, L., Banerjee, B.: Multi-agent reinforcement learning as a rehearsal for decentralized planning. Neurocomputing 190, 82\u201394 (2016)","journal-title":"Neurocomputing"},{"key":"2_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102678","volume":"117","author":"Z Lei","year":"2020","unstructured":"Lei, Z., Qian, X., Ukkusuri, S.V.: Efficient proactive vehicle relocation for on-demand mobility service with recurrent neural networks. Transp. Res. Part C: Emerg. Technol. 117, 102678 (2020)","journal-title":"Transp. Res. Part C: Emerg. Technol."},{"key":"2_CR21","unstructured":"Liang, E., et al.: RLlib: abstractions for distributed reinforcement learning. In: International Conference on Machine Learning (ICML) (2018)"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Lin, K., Zhao, R., Xu, Z., Zhou, J.: Efficient large-scale fleet management via multi-agent deep reinforcement learning. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2018)","DOI":"10.1145\/3219819.3219993"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Liu, N., et al.: A hierarchical framework of cloud resource allocation and power management using deep reinforcement learning. In: 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS), pp. 372\u2013382. IEEE (2017)","DOI":"10.1109\/ICDCS.2017.123"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Makar, R., Mahadevan, S., Ghavamzadeh, M.: Hierarchical multi-agent reinforcement learning. In: Proceedings of the Fifth International Conference on Autonomous Agents, pp. 246\u2013253 (2001)","DOI":"10.1145\/375735.376302"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Mao, H., Alizadeh, M., Menache, I., Kandula, S.: Resource management with deep reinforcement learning. In: Proceedings of the 15th ACM Workshop on Hot Topics in Networks, pp. 50\u201356 (2016)","DOI":"10.1145\/3005745.3005750"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Mao, H., Schwarzkopf, M., Venkatakrishnan, S.B., Meng, Z., Alizadeh, M.: Learning scheduling algorithms for data processing clusters. In: Proceedings of the ACM Special Interest Group on Data Communication, pp. 270\u2013288 (2019)","DOI":"10.1145\/3341302.3342080"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Ming, G.F., Hua, S.: Course-scheduling algorithm of option-based hierarchical reinforcement learning. In: 2010 Second International Workshop on Education Technology and Computer Science, vol. 1, pp. 288\u2013291. IEEE (2010)","DOI":"10.1109\/ETCS.2010.584"},{"issue":"7540","key":"2_CR28","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"},{"key":"2_CR29","unstructured":"Nachum, O., Gu, S.S., Lee, H., Levine, S.: Data-efficient hierarchical reinforcement learning. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018)"},{"key":"2_CR30","unstructured":"Papoudakis, G., Christianos, F., Rahman, A., Albrecht, S.V.: Dealing with non-stationarity in multi-agent deep reinforcement learning. arXiv preprint arXiv:1906.04737 (2019)"},{"key":"2_CR31","unstructured":"Parr, R., Russell, S.: Reinforcement learning with hierarchies of machines. Advances in Neural Information Processing Systems, pp. 1043\u20131049 (1998)"},{"key":"2_CR32","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"issue":"1\u20132","key":"2_CR33","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":"2_CR34","unstructured":"Tang, H., et al.: Hierarchical deep multiagent reinforcement learning with temporal abstraction. arXiv preprint arXiv:1809.09332 (2018)"},{"key":"2_CR35","unstructured":"Terry, J.K., Grammel, N., Hari, A., Santos, L., Black, B.: Revisiting parameter sharing in multi-agent deep reinforcement learning. arXiv preprint arXiv:2005.13625 (2020)"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Ye, H., Li, G.Y.: Deep reinforcement learning for resource allocation in v2v communications. In: 2018 IEEE International Conference on Communications (ICC), pp. 1\u20136. IEEE (2018)","DOI":"10.1109\/ICC.2018.8422586"}],"container-title":["Lecture Notes in Computer Science","Progress in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16474-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T14:17:51Z","timestamp":1662992271000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16474-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164736","9783031164743"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16474-3_2","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":"13 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EPIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"EPIA Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"epia2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/epia2022.inesc-id.pt\/","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":"85","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":"64","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":"75% - 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":"3,7","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":"0,9","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)"}}]}}