{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:35:54Z","timestamp":1742913354337,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031777301"},{"type":"electronic","value":"9783031777318"}],"license":[{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T00:00:00Z","timestamp":1731542400000},"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\/978-3-031-77731-8_34","type":"book-chapter","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T16:42:19Z","timestamp":1732034539000},"page":"375-386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cooperative-Competitive Decision-Making in Resource Management: A Reinforcement Learning Perspective"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2938-0575","authenticated-orcid":false,"given":"Artem","family":"Isakov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2855-9207","authenticated-orcid":false,"given":"Danil","family":"Peregorodiev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5569-4502","authenticated-orcid":false,"given":"Pavel","family":"Brunko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1886-2867","authenticated-orcid":false,"given":"Ivan","family":"Tomilov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1361-6037","authenticated-orcid":false,"given":"Natalia","family":"Gusarova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5483-716X","authenticated-orcid":false,"given":"Alexandra","family":"Vatian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,14]]},"reference":[{"key":"34_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2023.103357","volume":"154","author":"J Lei","year":"2024","unstructured":"Lei, J., Tan, D., Ma, X., Wang, Y.: Reinforcement learning based multi-parameter joint optimization in dense multi-hop wireless networks. Ad Hoc Netw. 154, 103357 (2024)","journal-title":"Ad Hoc Netw."},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Nicolas, P.G., Paul-Antoine, B.: Deep hierarchical reinforcement learning to manage the trade-off between sustainability and profitability in common pool resources systems. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137. IEEE (2021)","DOI":"10.1109\/IJCNN52387.2021.9534024"},{"key":"34_CR3","first-page":"9983","volume":"33","author":"A Pretorius","year":"2020","unstructured":"Pretorius, A., et al.: A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning. Adv. Neural Inf. Process. Syst. 33, 9983\u20139994 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"17","key":"34_CR4","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8121\/abe67b","volume":"54","author":"M Alqahtani","year":"2021","unstructured":"Alqahtani, M., Grafke, T.: Instantons for rare events in heavy-tailed distributions. J. Phys. A: Math. Theor. 54(17), 175001 (2021)","journal-title":"J. Phys. A: Math. Theor."},{"issue":"5","key":"34_CR5","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/MIS.2023.3265868","volume":"38","author":"X Liu","year":"2023","unstructured":"Liu, X., Liu, S., An, B., Gao, Y., Yang, S., Li, W.: Effective interpretable policy distillation via critical experience point identification. IEEE Intell. Syst. 38(5), 28\u201336 (2023)","journal-title":"IEEE Intell. Syst."},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Canese, L., et al.: Multi-agent reinforcement learning: a review of challenges and applications. Appl. Sci. 11(11), 4948 (2021)","DOI":"10.3390\/app11114948"},{"key":"34_CR7","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inf. Process. Syst. 30, (2017)"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Bellingham, J., Tillerson, M., Richards, A., How, J.: Multi-task allocation and path planning for cooperating UAVs. In: Cooperative Control: Models, Applications and Algorithms, pp. 23\u201341 (2003)","DOI":"10.1007\/978-1-4757-3758-5_2"},{"key":"34_CR9","doi-asserted-by":"crossref","unstructured":"Alighanbari, M.: Task assignment algorithms for teams of UAVs in dynamic environments (Doctoral dissertation, Massachusetts Institute of Technology) (2004)","DOI":"10.2514\/6.2004-5251"},{"key":"34_CR10","doi-asserted-by":"publisher","first-page":"146264","DOI":"10.1109\/ACCESS.2019.2943253","volume":"7","author":"H Qie","year":"2019","unstructured":"Qie, H., Shi, D., Shen, T., Xu, X., Li, Y., Wang, L.: Joint optimization of multi-UAV target assignment and path planning based on multi-agent reinforcement learning. IEEE Access 7, 146264\u2013146272 (2019)","journal-title":"IEEE Access"},{"issue":"13","key":"34_CR11","doi-asserted-by":"publisher","first-page":"4316","DOI":"10.1080\/00207543.2021.1973138","volume":"60","author":"M Panzer","year":"2022","unstructured":"Panzer, M., Bender, B.: Deep reinforcement learning in production systems: a systematic literature review. Int. J. Prod. Res. 60(13), 4316\u20134341 (2022)","journal-title":"Int. J. Prod. Res."},{"issue":"8","key":"34_CR12","doi-asserted-by":"publisher","first-page":"2461","DOI":"10.3390\/s24082461","volume":"24","author":"MN Al-Hamadani","year":"2024","unstructured":"Al-Hamadani, M.N., Fadhel, M.A., Alzubaidi, L., Harangi, B.: Reinforcement learning algorithms and applications in healthcare and robotics: a comprehensive and systematic review. Sensors 24(8), 2461 (2024)","journal-title":"Sensors"},{"key":"34_CR13","doi-asserted-by":"publisher","first-page":"122995","DOI":"10.1109\/ACCESS.2021.3110242","volume":"9","author":"Y Zhao","year":"2021","unstructured":"Zhao, Y., Wang, Y., Tan, Y., Zhang, J., Yu, H.: Dynamic jobshop scheduling algorithm based on deep Q network. IEEE Access 9, 122995\u2013123011 (2021)","journal-title":"IEEE Access"},{"issue":"2","key":"34_CR14","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1137\/20M131309X","volume":"3","author":"B Adcock","year":"2021","unstructured":"Adcock, B., Dexter, N.: The gap between theory and practice in function approximation with deep neural networks. SIAM J. Math. Data Sci. 3(2), 624\u2013655 (2021)","journal-title":"SIAM J. Math. Data Sci."},{"key":"34_CR15","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2021.550030","volume":"4","author":"L Wells","year":"2021","unstructured":"Wells, L., Bednarz, T.: Explainable AI and reinforcement learning\u2013a systematic review of current approaches and trends. Front. Artif. Intell. 4, 550030 (2021)","journal-title":"Front. Artif. Intell."},{"key":"34_CR16","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1007\/s10458-019-09418-w","volume":"33","author":"O Amir","year":"2019","unstructured":"Amir, O., Doshi-Velez, F., Sarne, D.: Summarizing agent strategies. Auton. Agent. Multi Agent Syst. 33, 628\u2013644 (2019)","journal-title":"Auton. Agent. Multi Agent Syst."},{"key":"34_CR17","unstructured":"Lage, I., Lifschitz, D., Doshi-Velez, F., Amir, O.: Toward robust policy summarization. In: Autonomous Agents and Multi-agent Systems, pp. 2081 (2019)"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Ehsan, U., Tambwekar, P., Chan, L., Harrison, B., Riedl, M.O.: Automated rationale generation: a technique for explainable AI and its effects on human perceptions. In: Proceedings of the 24th International Conference on Intelligent User Interfaces, pp. 263\u2013274 (2019)","DOI":"10.1145\/3301275.3302316"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Tabrez, A., Hayes, B.: Improving human-robot interaction through explainable reinforcement learning. In: 2019 14th ACM\/IEEE International Conference on Human-Robot Interaction (HRI), pp. 751\u2013753. IEEE (2019)","DOI":"10.1109\/HRI.2019.8673198"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Dethise, A., Canini, M., Kandula, S.: Cracking open the black box: what observations can tell us about reinforcement learning agents. In: Proceedings of the 2019 Workshop on Network Meets AI & ML, pp. 29-36 (2019)","DOI":"10.1145\/3341216.3342210"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Pan, X., Chen, X., Cai, Q., Canny, J., Yu, F.: Semantic predictive control for explainable and efficient policy learning. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 3203\u20133209 IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794437"},{"key":"34_CR22","doi-asserted-by":"publisher","first-page":"133653","DOI":"10.1109\/ACCESS.2019.2941229","volume":"7","author":"B Jang","year":"2019","unstructured":"Jang, B., Kim, M., Harerimana, G., Kim, J.W.: Q-learning algorithms: a comprehensive classification and applications. IEEE Access 7, 133653\u2013133667 (2019)","journal-title":"IEEE Access"},{"issue":"3","key":"34_CR23","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.aaen.2006.06.002","volume":"14","author":"S Williams","year":"2006","unstructured":"Williams, S., Crouch, R.: Emergency department patient classification systems: a systematic review. Accid. Emerg. Nurs. 14(3), 160\u2013170 (2006)","journal-title":"Accid. Emerg. Nurs."},{"key":"34_CR24","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387\u2013395 (2014)"},{"issue":"8","key":"34_CR25","doi-asserted-by":"publisher","first-page":"8043","DOI":"10.1007\/s10462-022-10359-2","volume":"56","author":"A Morales-Hern\u00e1ndez","year":"2023","unstructured":"Morales-Hern\u00e1ndez, A., Van Nieuwenhuyse, I., Rojas Gonzalez, S.: A survey on multi-objective hyperparameter optimization algorithms for machine learning. Artif. Intell. Rev. 56(8), 8043\u20138093 (2023)","journal-title":"Artif. Intell. Rev."},{"key":"34_CR26","unstructured":"Ustaran-Anderegg, N., Pratt, M.: AgileRL [Computer software]. https:\/\/github.com\/AgileRL\/AgileRL"},{"issue":"9","key":"34_CR27","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1177\/0037549706073695","volume":"82","author":"SF Railsback","year":"2006","unstructured":"Railsback, S.F., Lytinen, S.L., Jackson, S.K.: Agent-based simulation platforms: review and development recommendations. Simulation 82(9), 609\u2013623 (2006)","journal-title":"Simulation"},{"key":"34_CR28","first-page":"15032","volume":"34","author":"J Terry","year":"2021","unstructured":"Terry, J., et al.: Pettingzoo: gym for multi-agent reinforcement learning. Adv. Neural Inf. Process. Syst. 34, 15032\u201315043 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, K., Yang, Z., Ba\u015far, T.: Multi-agent reinforcement learning: A selective overview of theories and algorithms. In: Handbook of Reinforcement Learning and Control, pp. 321\u2013384 (2021)","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., Koyama, M.: Optuna: a next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2623\u20132631 (2019)","DOI":"10.1145\/3292500.3330701"}],"container-title":["Lecture Notes in Computer Science","Intelligent Data Engineering and Automated Learning \u2013 IDEAL 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77731-8_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T16:47:15Z","timestamp":1732034835000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77731-8_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,14]]},"ISBN":["9783031777301","9783031777318"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77731-8_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,14]]},"assertion":[{"value":"14 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors declare that there are no conflicts of interest regarding the publication of this article. This research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"IDEAL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Data Engineering and Automated Learning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Valencia","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ideal2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}