{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:48:42Z","timestamp":1776358122985,"version":"3.51.2"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,2,10]],"date-time":"2024-02-10T00:00:00Z","timestamp":1707523200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,10]],"date-time":"2024-02-10T00:00:00Z","timestamp":1707523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032018"],"award-info":[{"award-number":["62032018"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Machine Teaching for Explainable AI","award":["329745"],"award-info":[{"award-number":["329745"]}]},{"name":"the Future of Life Institute, FLI","award":["RFP2-152"],"award-info":[{"award-number":["RFP2-152"]}]},{"name":"the EU (FEDER) and Spanish grant","award":["RTI2018-094403-B-C32"],"award-info":[{"award-number":["RTI2018-094403-B-C32"]}]},{"name":"EU\u2019s Horizon 2020 research and innovation programme under grant agreement","award":["952215"],"award-info":[{"award-number":["952215"]}]},{"name":"Spanish grant","award":["PID2021-122830OB-C42"],"award-info":[{"award-number":["PID2021-122830OB-C42"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Team formation in multi-agent systems usually assumes the capabilities of each team member are known, and the best formation can be derived from that information. As AI agents become more sophisticated, this characterisation is becoming more elusive and less predictive about the performance of a team in cooperative or competitive situations. In this paper, we introduce a general and flexible way of anticipating the outcome of a game for any lineups (the agents, sociality regimes and any other hyperparameters for the team). To this purpose, we simply train an assessor using an appropriate team representation and standard machine learning techniques. We illustrate how we can interrogate the assessor to find the best formations in a pursuit\u2013evasion game for several scenarios: offline team formation, where teams have to be decided before the game and not changed afterwards, and online team formation, where teams can see the lineups of the other teams and can be changed at any time.<\/jats:p>","DOI":"10.1007\/s40747-023-01336-5","type":"journal-article","created":{"date-parts":[[2024,2,10]],"date-time":"2024-02-10T14:02:08Z","timestamp":1707573728000},"page":"3473-3492","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Team formation through an assessor: choosing MARL agents in pursuit\u2013evasion games"],"prefix":"10.1007","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0664-4769","authenticated-orcid":false,"given":"Yue","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Lushan","family":"Ju","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9746-7632","authenticated-orcid":false,"given":"Jos\u00e8","family":"Hern\u00e1ndez-Orallo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,10]]},"reference":[{"issue":"7","key":"1336_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3465399","volume":"54","author":"J Ju\u00e1rez","year":"2021","unstructured":"Ju\u00e1rez J, Santos C, Brizuela CA (2021) A comprehensive review and a taxonomy proposal of team formation problems. ACM Comput Surv (CSUR) 54(7):1\u201333","journal-title":"ACM Comput Surv (CSUR)"},{"issue":"1","key":"1336_CR2","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1162\/artl_a_00390","volume":"29","author":"HL Kwa","year":"2023","unstructured":"Kwa HL, Babineau V, Philippot J, Bouffanais R (2023) Adapting the exploration-exploitation balance in heterogeneous swarms: tracking evasive targets. Artif Life 29(1):21\u201336","journal-title":"Artif Life"},{"key":"1336_CR3","doi-asserted-by":"crossref","unstructured":"Shishika D, Paulos J, Dorothy MR, Hsieh MA, Kumar V (2019) Team composition for perimeter defense with patrollers and defenders. In: 2019 IEEE 58th conference on decision and control (CDC). IEEE, pp 7325\u20137332","DOI":"10.1109\/CDC40024.2019.9030082"},{"key":"1336_CR4","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.chb.2018.07.018","volume":"101","author":"Y-S Jeong","year":"2019","unstructured":"Jeong Y-S, Pan Y, Rathore S, Kim B, Park JH (2019) A parallel team formation approach using crowd intelligence from social network. Comput Hum Behav 101:429\u2013434","journal-title":"Comput Hum Behav"},{"key":"1336_CR5","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s11280-019-00712-x","volume":"23","author":"L Chen","year":"2020","unstructured":"Chen L, Ye Y, Zheng A, Xie F, Zheng Z, Lyu MR (2020) Incorporating geographical location for team formation in social coding sites. World Wide Web 23:153\u2013174","journal-title":"World Wide Web"},{"key":"1336_CR6","doi-asserted-by":"crossref","unstructured":"Reslan M, Hastings EM, Brundage MP, Sexton T (2021) A data-driven framework for team formation for maintenance tasks. Int J Progn Health Manag 12(1). https:\/\/papers.phmsociety.org\/index.php\/ijphm\/article\/view\/2930","DOI":"10.36001\/ijphm.2021.v12i1.2930"},{"key":"1336_CR7","doi-asserted-by":"crossref","unstructured":"Liemhetcharat S, Veloso M (2014) Weighted synergy graphs for effective team formation with heterogeneous ad hoc agents. Artif Intell 208:41\u201365.","DOI":"10.1016\/j.artint.2013.12.002"},{"key":"1336_CR8","doi-asserted-by":"crossref","unstructured":"Weintraub IE, Pachter M, Garcia E (2020) An introduction to pursuit-evasion differential games. In: 2020 American Control Conference (ACC). IEEE, pp 1049\u20131066","DOI":"10.23919\/ACC45564.2020.9147205"},{"key":"1336_CR9","doi-asserted-by":"crossref","unstructured":"Zhang Y, Guo Q, An B, Tran-Thanh L, Jennings NR (2019) Optimal interdiction of urban criminals with the aid of real-time information. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 1262\u20131269","DOI":"10.1609\/aaai.v33i01.33011262"},{"key":"1336_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.112742","volume":"266","author":"Z Sun","year":"2022","unstructured":"Sun Z, Sun H, Li P, Zou J (2022) Cooperative strategy for pursuit-evasion problem with collision avoidance. Ocean Eng 266:112742","journal-title":"Ocean Eng"},{"issue":"8","key":"1336_CR11","doi-asserted-by":"publisher","first-page":"211","DOI":"10.3390\/aerospace8080211","volume":"8","author":"Z Wang","year":"2021","unstructured":"Wang Z, Gong B, Yuan Y, Ding X (2021) Incomplete information pursuit-evasion game control for a space non-cooperative target. Aerospace 8(8):211","journal-title":"Aerospace"},{"key":"1336_CR12","unstructured":"Agapiou JP, Vezhnevets AS, Du\u00e9\u00f1ez-Guzm\u00e1n EA, Matyas J, Mao Y, Sunehag P, K\u00f6ster R, Madhushani U, Kopparapu K, Comanescu R et al (2022) Melting pot 2.0. arXiv preprint arXiv:2211.13746"},{"issue":"3","key":"1336_CR13","doi-asserted-by":"publisher","first-page":"4257","DOI":"10.1109\/LRA.2020.2994023","volume":"5","author":"E Garcia","year":"2020","unstructured":"Garcia E, Casbeer DW, Pachter M (2020) Optimal strategies for a class of multi-player reach-avoid differential games in 3d space. IEEE Robot Autom Lett 5(3):4257\u20134264","journal-title":"IEEE Robot Autom Lett"},{"issue":"3","key":"1336_CR14","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1109\/TAC.2016.2577619","volume":"62","author":"M Chen","year":"2016","unstructured":"Chen M, Zhou Z, Tomlin CJ (2016) Multiplayer reach-avoid games via pairwise outcomes. IEEE Trans Autom Control 62(3):1451\u20131457","journal-title":"IEEE Trans Autom Control"},{"issue":"11","key":"1336_CR15","doi-asserted-by":"crossref","first-page":"4189","DOI":"10.3934\/dcdsb.2020093","volume":"25","author":"R Zou","year":"2020","unstructured":"Zou R, Guo S (2020) Dynamics of a diffusive Leslie-Gower predator-prey model in spatially heterogeneous environment. Discrete Contin Dyn Syst Ser B 25(11):4189\u20134210","journal-title":"Discrete Contin Dyn Syst Ser B"},{"key":"1336_CR16","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1007\/s13235-019-00319-x","volume":"9","author":"VR Makkapati","year":"2019","unstructured":"Makkapati VR, Tsiotras P (2019) Optimal evading strategies and task allocation in multi-player pursuit-evasion problems. Dyn Games Appl 9:1168\u20131187","journal-title":"Dyn Games Appl"},{"issue":"5","key":"1336_CR17","doi-asserted-by":"publisher","first-page":"2345","DOI":"10.1109\/TAC.2020.3003840","volume":"66","author":"E Garcia","year":"2020","unstructured":"Garcia E, Casbeer DW, Von Moll A, Pachter M (2020) Multiple pursuer multiple evader differential games. IEEE Trans Autom Control 66(5):2345\u20132350","journal-title":"IEEE Trans Autom Control"},{"key":"1336_CR18","unstructured":"Son K, Kim D, Kang WJ, Hostallero DE, Yi Y (2019) Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: International conference on machine learning. PMLR, pp 5887\u20135896"},{"key":"1336_CR19","unstructured":"Kim W, Park J, Sung Y (2021) Communication in multi-agent reinforcement learning: intention sharing. In: International conference on learning representations"},{"key":"1336_CR20","unstructured":"Yang Y, Yu L, Bai Y, Wang J, Zhang W, Wen Y, Yu Y (2017) A study of AI population dynamics with million-agent reinforcement learning. arXiv preprint arXiv:1709.04511"},{"key":"1336_CR21","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez-Orallo J, Schellaert W, Mart\u00ednez-Plumed F (2022) Training on the test set: Mapping the system-problem space in AI. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, pp 12256\u201312261","DOI":"10.1609\/aaai.v36i11.21487"},{"key":"1336_CR22","first-page":"6382","volume":"30","author":"R Lowe","year":"2017","unstructured":"Lowe R, Wu YI, Tamar A, Harb J, Pieter Abbeel O, Mordatch I (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. Adv Neural Inf Process Syst 30:6382\u20136393","journal-title":"Adv Neural Inf Process Syst"},{"key":"1336_CR23","doi-asserted-by":"crossref","unstructured":"Mordatch I, Abbeel P (2018) Emergence of grounded compositional language in multi-agent populations. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"1336_CR24","doi-asserted-by":"crossref","unstructured":"Li S, Wu Y, Cui X, Dong H, Fang F, Russell S (2019) Robust multi-agent reinforcement learning via minimax deep deterministic policy gradient. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 4213\u20134220","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"1336_CR25","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971"},{"key":"1336_CR26","doi-asserted-by":"publisher","unstructured":"Zhao Y, Hern\u00e1ndez-Orallo J (2022) When being selfish prevails: The impact of sociality regimes on heterogeneous cooperative-competitive multi-agent reinforcement learning. Preprint from Research Square. https:\/\/doi.org\/10.21203\/rs.3.rs-2411520\/v1","DOI":"10.21203\/rs.3.rs-2411520\/v1"},{"issue":"6","key":"1336_CR27","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1177\/0963721415599543","volume":"24","author":"AW Woolley","year":"2015","unstructured":"Woolley AW, Aggarwal I, Malone TW (2015) Collective intelligence and group performance. Curr Dir Psychol Sci 24(6):420\u2013424","journal-title":"Curr Dir Psychol Sci"},{"issue":"1","key":"1336_CR28","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s10458-022-09548-8","volume":"36","author":"KR McKee","year":"2022","unstructured":"McKee KR, Leibo JZ, Beattie C, Everett R (2022) Quantifying the effects of environment and population diversity in multi-agent reinforcement learning. Auton Agents Multi-Agent Syst 36(1):21","journal-title":"Auton Agents Multi-Agent Syst"},{"key":"1336_CR29","unstructured":"Okimoto T, Ribeiro T, Bouchabou D, Inoue K (2016) Mission oriented robust multi-team formation and its application to robot rescue simulation. In: Twenty-fifth international joint conference on artificial intelligence (IJCAI-16)"},{"issue":"1","key":"1336_CR30","doi-asserted-by":"publisher","first-page":"29","DOI":"10.5465\/annals.2017.0131","volume":"14","author":"M Lazar","year":"2020","unstructured":"Lazar M, Miron-Spektor E, Agarwal R, Erez M, Goldfarb B, Chen G (2020) Entrepreneurial team formation. Acad Manag Ann 14(1):29\u201359","journal-title":"Acad Manag Ann"},{"key":"1336_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.106061","volume":"106","author":"H Liu","year":"2020","unstructured":"Liu H, Lyu Y, Zhao W (2020) Robust visual servoing formation tracking control for quadrotor UAV team. Aerosp Sci Technol 106:106061","journal-title":"Aerosp Sci Technol"},{"key":"1336_CR32","unstructured":"Shaw L, Glickman M (2019) Dynamic analysis of team strategy in professional football. Bar\u00e7a sports analytics summit 13"},{"issue":"2","key":"1336_CR33","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1016\/j.ejor.2015.08.047","volume":"249","author":"C Akkan","year":"2016","unstructured":"Akkan C, K\u00fcl\u00fcnk ME, Ko\u00e7A\u015f C (2016) Finding robust timetables for project presentations of student teams. Eur J Oper Res 249(2):560\u2013576","journal-title":"Eur J Oper Res"},{"key":"1336_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114886","volume":"177","author":"K Selvarajah","year":"2021","unstructured":"Selvarajah K, Zadeh PM, Kobti Z, Palanichamy Y, Kargar M (2021) A unified framework for effective team formation in social networks. Expert Syst Appl 177:114886","journal-title":"Expert Syst Appl"},{"key":"1336_CR35","unstructured":"Liemhetcharat S, Veloso M (2012) Modeling and learning synergy for team formation with heterogeneous agents. In: Proceedings of the 11th international conference on autonomous agents and multiagent systems, vol 1, pp 365\u2013374"},{"key":"1336_CR36","unstructured":"Esgario J, Silva IED, Krohling RA (2019) Application of genetic algorithms to the multiple team formation problem. arXiv:1903.03523"},{"key":"1336_CR37","doi-asserted-by":"crossref","unstructured":"Bello M, Bello R, Now\u00e9 A, Garc\u00eda-Lorenzo MM (2018) A method for the team selection problem between two decision-makers using the ant colony optimization. Soft computing applications for group decision-making and consensus modeling, pp 391\u2013410","DOI":"10.1007\/978-3-319-60207-3_23"},{"key":"1336_CR38","doi-asserted-by":"crossref","unstructured":"Yannibelli VD, Amandi AA (2018) Collaborative learning team formation considering team roles: an evolutionary approach based on adaptive crossover, mutation and simulated annealing","DOI":"10.13053\/rcs-147-4-5"},{"key":"1336_CR39","doi-asserted-by":"crossref","unstructured":"Matthews T, Ramchurn S, Chalkiadakis G (2012) Competing with humans at fantasy football: Team formation in large partially-observable domains. In: Proceedings of the AAAI conference on artificial intelligence, vol 26, pp 1394\u20131400","DOI":"10.1609\/aaai.v26i1.8259"},{"key":"1336_CR40","first-page":"15786","volume":"33","author":"B Baker","year":"2020","unstructured":"Baker B (2020) Emergent reciprocity and team formation from randomized uncertain social preferences. Adv Neural Inf Process Syst 33:15786\u201315799","journal-title":"Adv Neural Inf Process Syst"},{"key":"1336_CR41","unstructured":"Chalkiadakis G, Boutilier C (2004) Bayesian reinforcement learning for coalition formation under uncertainty. In: Proceedings of the third international joint conference on autonomous agents and multiagent systems, vol 3, pp 1090\u20131097"},{"key":"1336_CR42","doi-asserted-by":"crossref","unstructured":"Rothe J (2021) Thou shalt love thy neighbor as thyself when thou playest: altruism in game theory. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 15070\u201315077","DOI":"10.1609\/aaai.v35i17.17770"},{"key":"1336_CR43","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"key":"1336_CR44","unstructured":"Dhariwal P, Hesse C, Klimov O, Nichol A, Plappert M, Radford A, Schulman J, Sidor S, Wu Y, Zhokhov P (2016) Openai baselines. https:\/\/github.com\/openai\/baselines"},{"key":"1336_CR45","unstructured":"Yu C, Velu A, Vinitsky E, Wang Y, Bayen A, Wu Y (2021) The surprising effectiveness of ppo in cooperative, multi-agent games. arXiv preprint arXiv:2103.01955"},{"key":"1336_CR46","doi-asserted-by":"crossref","unstructured":"Wang N, Das GP, Millard AG (2022) Learning cooperative behaviours in adversarial multi-agent systems. In: Towards autonomous robotic systems, proceedings. Springer, pp 179\u2013189","DOI":"10.1007\/978-3-031-15908-4_15"},{"key":"1336_CR47","unstructured":"Papoudakis G, Christianos F, Sch\u00e4fer L, Albrecht SV (2020) Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks. arXiv preprint arXiv:2006.07869"},{"key":"1336_CR48","unstructured":"Zhou L, Mart\u00ednez-Plumed F, Hern\u00e1ndez-Orallo J, Ferri C, Schellaert W (2022) Reject before you run: small assessors anticipate big language models. https:\/\/ceur-ws.org\/Vol-3169\/paper4.pdf"},{"key":"1336_CR49","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 785\u2013794","DOI":"10.1145\/2939672.2939785"},{"key":"1336_CR50","first-page":"4768","volume":"30","author":"SM Lundberg","year":"2017","unstructured":"Lundberg SM, Lee S-I (2017) A unified approach to interpreting model predictions. Adv Neural Inf Process Syst 30:4768\u20134777","journal-title":"Adv Neural Inf Process Syst"},{"issue":"6641","key":"1336_CR51","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1126\/science.adf6369","volume":"380","author":"R Burnell","year":"2023","unstructured":"Burnell R, Schellaert W, Burden J, Ullman TD, Martinez-Plumed F, Tenenbaum JB, Rutar D, Cheke LG, Sohl-Dickstein J, Mitchell M, Kiela D, Shanahan M, Voorhees EM, Cohn AG, Leibo JZ, Hernandez-Orallo J (2023) Rethink reporting of evaluation results in AI. Science 380(6641):136\u2013138. https:\/\/doi.org\/10.1126\/science.adf6369","journal-title":"Science"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01336-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-023-01336-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-023-01336-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:40:16Z","timestamp":1731285616000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-023-01336-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,10]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["1336"],"URL":"https:\/\/doi.org\/10.1007\/s40747-023-01336-5","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,10]]},"assertion":[{"value":"31 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This research did not contain any studies involving animal or human participants, nor did it take place in any private or protected areas. No specific permissions were required for corresponding locations. Informed consent was obtained from all individual participants included in the study. All authors of this paper \u201cTeam Formation through an Assessor: Choosing MARL Agents in Pursuit\u2013Evasion Games\u201d have read and approved the final version submitted.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}