{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T02:42:58Z","timestamp":1775011378545,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819688883","type":"print"},{"value":"9789819688890","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":[[2026]]},"DOI":"10.1007\/978-981-96-8889-0_15","type":"book-chapter","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T08:56:35Z","timestamp":1751273795000},"page":"175-187","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Multi-agent Reinforcement Learning with\u00a0Epistemic Priors for\u00a0Scalable Communicationless Coordination of Teamable Agents"],"prefix":"10.1007","author":[{"given":"Thayne T.","family":"Walker","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaime S.","family":"Ide","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,1]]},"reference":[{"issue":"1","key":"15_CR1","doi-asserted-by":"publisher","first-page":"363","DOI":"10.3390\/app11010363","volume":"11","author":"JJ Rold\u00e1n-G\u00f3mez","year":"2021","unstructured":"Rold\u00e1n-G\u00f3mez, J.J., Gonz\u00e1lez-Gironda, E., Barrientos, A.: A survey on robotic technologies for forest firefighting: applying drone swarms to improve firefighters\u2019 efficiency and safety. Appl. Sci. 11(1), 363 (2021)","journal-title":"Appl. Sci."},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Arnold, R., Jablonski, J., Abruzzo, B., Mezzacappa, E.: Heterogeneous UAV multi-role swarming behaviors for search and rescue. In: 2020 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA), pp. 122\u2013128. IEEE (2020)","DOI":"10.1109\/CogSIMA49017.2020.9215994"},{"issue":"3","key":"15_CR3","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3390\/drones3030059","volume":"3","author":"H Hildmann","year":"2019","unstructured":"Hildmann, H., Kovacs, E.: Using unmanned aerial vehicles (UAVs) as mobile sensing platforms (MSPs) for disaster response, civil security and public safety. Drones 3(3), 59 (2019)","journal-title":"Drones"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Fu, Q., Qiu, T., Yi, J., Pu, Z., Wu, S.: Concentration network for reinforcement learning of large-scale multi-agent systems. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 9, pp. 9341\u20139349 (2022)","DOI":"10.1609\/aaai.v36i9.21165"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Jyothi, S.A., Singla, A., Godfrey, P.B., Kolla, A.: Measuring and understanding throughput of network topologies. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 201616, pp. 761\u2013772 (2016)","DOI":"10.1109\/SC.2016.64"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Ekanayake, S.W., Pathirana, P.N., Rolfe, B.F., Palaniswami, M.: Energy efficient, fully-connected mesh networks for high speed applications. In: VTC Spring 2008-IEEE Vehicular Technology Conference, pp. 2606\u20132610. IEEE (2008)","DOI":"10.1109\/VETECS.2008.572"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Walker, T.T., Ide, J.S., Choi, M., Guarino, M., Alcedo, K.: Multi-agent reinforcement learning with epistemic priors. In: 2023 9th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 2514\u20132518. IEEE (2023)","DOI":"10.1109\/CoDIT58514.2023.10284342"},{"issue":"4","key":"15_CR8","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1017\/S0140525X00076512","volume":"1","author":"D Premack","year":"1978","unstructured":"Premack, D., Woodruff, G.: Does the chimpanzee have a theory of mind? Behav. Brain Sci. 1(4), 515\u2013526 (1978)","journal-title":"Behav. Brain Sci."},{"issue":"1","key":"15_CR9","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3166\/jancl.21.9-34","volume":"21","author":"T Bolander","year":"2011","unstructured":"Bolander, T., Andersen, M.B.: Epistemic planning for single-and multi-agent systems. J. Appl. Non-Classical Logics 21(1), 9\u201334 (2011)","journal-title":"J. Appl. Non-Classical Logics"},{"key":"15_CR10","unstructured":"Lowe, R., et al.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, vol.\u00a030 (2017)"},{"issue":"4","key":"15_CR11","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","volume":"27","author":"DS Bernstein","year":"2002","unstructured":"Bernstein, D.S., Givan, R., Immerman, N., Zilberstein, S.: The complexity of decentralized control of Markov decision processes. Math. Oper. Res. 27(4), 819\u2013840 (2002)","journal-title":"Math. Oper. Res."},{"key":"15_CR12","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":"15_CR13","doi-asserted-by":"crossref","unstructured":"Engesser, T., Bolander, T., Mattm\u00fcller, R., Nebel, B.: Cooperative epistemic multi-agent planning for implicit coordination. arXiv preprintarXiv:1703.02196 (2017)","DOI":"10.4204\/EPTCS.243.6"},{"key":"15_CR14","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":"15_CR15","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s10458-006-7035-4","volume":"13","author":"M Ghavamzadeh","year":"2006","unstructured":"Ghavamzadeh, M., Mahadevan, S., Makar, R.: Hierarchical multi-agent reinforcement learning. Auton. Agent. Multi-Agent Syst. 13, 197\u2013229 (2006)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"15_CR16","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1016\/j.engappai.2016.12.018","volume":"59","author":"A Farinelli","year":"2017","unstructured":"Farinelli, A., Bicego, M., Bistaffa, F., Ramchurn, S.D.: A hierarchical clustering approach to large-scale near-optimal coalition formation with quality guarantees. Eng. Appl. Artif. Intell. 59, 170\u2013185 (2017)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Pancanti, S., Pallottino, L., Salvadorini, D., Bicchi, A.: Motion planning through symbols and lattices. In: IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA 2004. 2004, vol.\u00a04, pp. 3914\u20133919. IEEE (2004)","DOI":"10.1109\/ROBOT.2004.1308878"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Pope, A.P., et al.: Hierarchical reinforcement learning for air-to-air combat. In: 2021 International Conference on Unmanned Aircraft Systems (ICUAS), pp. 275\u2013284. IEEE (2021)","DOI":"10.1109\/ICUAS51884.2021.9476700"},{"issue":"2","key":"15_CR19","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/0004-3702(74)90026-5","volume":"5","author":"ED Sacerdoti","year":"1974","unstructured":"Sacerdoti, E.D.: Planning in a hierarchy of abstraction spaces. Artif. Intell. 5(2), 115\u2013135 (1974)","journal-title":"Artif. Intell."},{"issue":"1\u20132","key":"15_CR20","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/0004-3702(95)00111-5","volume":"85","author":"RC Holte","year":"1996","unstructured":"Holte, R.C., Mkadmi, T., Zimmer, R.M., MacDonald, A.J.: Speeding up problem solving by abstraction: a graph oriented approach. Artif. Intell. 85(1\u20132), 321\u2013361 (1996)","journal-title":"Artif. Intell."},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Deka, A., Sycara, K.: Natural emergence of heterogeneous strategies in artificially intelligent competitive teams. In: International Conference on Swarm Intelligence, pp. 13\u201325. Springer (2021)","DOI":"10.1007\/978-3-030-78743-1_2"},{"key":"15_CR22","doi-asserted-by":"publisher","unstructured":"Barto, A.G., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Discrete Event Dyn. Syst. 13(4), 341\u2013379 (2003). https:\/\/doi.org\/10.1023\/A:1025696116075","DOI":"10.1023\/A:1025696116075"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Yu, J., LaValle, S.M.: Multi-agent path planning and network flow. In: Algorithmic Foundations of Robotics X: Proceedings of the Tenth Workshop on the Algorithmic Foundations of Robotics, pp. 157\u2013173. Springer (2013)","DOI":"10.1007\/978-3-642-36279-8_10"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Ma, H., Koenig, S.: Optimal target assignment and path finding for teams of agents (2016)","DOI":"10.65109\/GOAC4514"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Gallici, M., Martin, M., Masmitja, I.: Transfqmix: transformers for leveraging the graph structure of multi-agent reinforcement learning problems arXiv preprintarXiv:2301.05334 (2023)","DOI":"10.65109\/LTKY8883"},{"key":"15_CR26","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":"15_CR27","unstructured":"Walker, T.T., Ide, J.S., Choi, M., Guarino, M.J., Alcedo, K.: Multi-agent reinforcement learning with epistemic priors. In: PRL Workshop Series $$\\{{\\backslash} textendash\\}$$Bridging the Gap Between AI Planning and Reinforcement Learning"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Khan, K., Rehman, S.U., Aziz, K., Fong, S., Sarasvady, S.: Dbscan: past, present and future. In: The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT, vol. 2014, pp. 232\u2013238. IEEE (2014)","DOI":"10.1109\/ICADIWT.2014.6814687"},{"key":"15_CR29","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/BF02614365","volume":"78","author":"JB Orlin","year":"1997","unstructured":"Orlin, J.B.: A polynomial time primal network simplex algorithm for minimum cost flows. Math. Program. 78, 109\u2013129 (1997)","journal-title":"Math. Program."},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"H\u00f6nig, W., et al.: Multi-agent path finding with kinematic constraints. In: Twenty-Sixth International Conference on Automated Planning and Scheduling (2016)","DOI":"10.24963\/ijcai.2017\/684"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Alshiekh, M., Bloem, R., Ehlers, R., K\u00f6nighofer, B., Niekum, S., Topcu, U.: Safe reinforcement learning via shielding. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032, no.\u00a01 (2018)","DOI":"10.1609\/aaai.v32i1.11797"}],"container-title":["Lecture Notes in Computer Science","Advances and Trends in Artificial Intelligence. Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-8889-0_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T01:34:48Z","timestamp":1775007288000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-8889-0_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"ISBN":["9789819688883","9789819688890"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-8889-0_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,1]]},"assertion":[{"value":"1 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IEA\/AIE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kytakyushu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"1 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ieaaie2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.i-somet.org\/iea-aie2025\/committees.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}