{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T10:29:30Z","timestamp":1772101770493,"version":"3.50.1"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2021,5,9]],"date-time":"2021-05-09T00:00:00Z","timestamp":1620518400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,9]],"date-time":"2021-05-09T00:00:00Z","timestamp":1620518400000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s11042-021-10968-z","type":"journal-article","created":{"date-parts":[[2021,5,9]],"date-time":"2021-05-09T01:02:29Z","timestamp":1620522149000},"page":"26773-26793","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Toward competitive multi-agents in Polo game based on reinforcement learning"],"prefix":"10.1007","volume":"80","author":[{"given":"Zahra","family":"Movahedi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7935-819X","authenticated-orcid":false,"given":"Azam","family":"Bastanfard","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,9]]},"reference":[{"key":"10968_CR1","doi-asserted-by":"crossref","unstructured":"Ali MZ, Morghem A, Albadarneh J, Al-Gharaibeh R, Suganthan PN, Reynolds RG (2014) Cultural algorithm applied to the evolution of robotic soccer team tactics: a novel perspective, Congress on Evolutionary Computation, IEEE, pp 2180\u20132187","DOI":"10.1109\/CEC.2014.6900616"},{"key":"10968_CR2","doi-asserted-by":"crossref","unstructured":"Asis KD, Hernandez-Garcia JF, Holland GZ, Sutton RS (2018) multi-step reinforcement learning: a unifying algorithm, 31th AAAI Conference on Artificial Intelligence 32:2902\u20132909","DOI":"10.1609\/aaai.v32i1.11631"},{"key":"10968_CR3","doi-asserted-by":"crossref","unstructured":"Baglivo A, Ponti FD, Luca DD, Guidazzoli A, Liguori MC (2013) X3D\/X3DOM, Blender Game Engine and OSG4WEB: open source visualization for cultural heritage environments. Digital Heritage Int Congress, IEEE 2:711\u2013718","DOI":"10.1109\/DigitalHeritage.2013.6744840"},{"key":"10968_CR4","doi-asserted-by":"crossref","unstructured":"Banerjee B, Davis CE (2017) Multi-agent path finding with persistence conflicts. IEEE Trans Comput Intell AI in Games, IEEE 9:402\u2013409","DOI":"10.1109\/TCIAIG.2016.2620060"},{"key":"10968_CR5","doi-asserted-by":"crossref","unstructured":"Beysolow T (2019) Applied reinforcement learning with Python, Book, Springer","DOI":"10.1007\/978-1-4842-5127-0"},{"key":"10968_CR6","doi-asserted-by":"crossref","unstructured":"Carmel D, Markovitch S (1998) Model-based learning of interaction strategies in multi-agent systems. Taylor & Francis Ltd 10:309\u2013332","DOI":"10.1080\/095281398146789"},{"key":"10968_CR7","doi-asserted-by":"crossref","unstructured":"Castelfranchi C, Lesperance Y (2000) Intelligent Agent VII\u2013Agent Theories, Architecture and Languages, Springer","DOI":"10.1007\/3-540-44631-1"},{"key":"10968_CR8","first-page":"447","volume":"128","author":"B Chen","year":"2014","unstructured":"Chen B, Zhang A, Cao L (2014) Autonomous intelligent decision-making system based on Bayesian SOM. Neural Netw Robot Soccer, Elsevier, Neurocomputing 128:447\u2013458","journal-title":"Neural Netw Robot Soccer, Elsevier, Neurocomputing"},{"key":"10968_CR9","doi-asserted-by":"crossref","unstructured":"Collazo MN, Cotta C, Fernandez-Leiva AJ (2014) Virtual player design using self-learning via competitive coevolutionary algorithms, Springer. Nat Comput 31:131\u2013144","DOI":"10.1007\/s11047-014-9411-3"},{"key":"10968_CR10","doi-asserted-by":"crossref","unstructured":"Collazo MN, Porras CC, Fern\u2019Andez-Leiva AJ (2016) Competitive algorithms for co-evolving both game content and AI a case of study: planet wars. IEEE Transactions on Computational Intelligence and AI in Games 8(4):325\u2013337","DOI":"10.1109\/TCIAIG.2015.2499281"},{"key":"10968_CR11","doi-asserted-by":"publisher","first-page":"21245","DOI":"10.1007\/s11042-017-5459-2","volume":"77","author":"A Covaci","year":"2018","unstructured":"Covaci A, Ghinea G, Huang CH, Shih J (2018) Multisensory came-lessons learnt from olfactory enhancement of a digital board game, Springer. Multimed Tools Appl 77:21245\u201321263","journal-title":"Multimed Tools Appl"},{"key":"10968_CR12","unstructured":"Danny W (2010) Architecture-based design of multi-agent systems. Springer"},{"key":"10968_CR13","doi-asserted-by":"crossref","unstructured":"Ding S, Du W, Zhao X, Wang L, Jia W (2019) A new asynchronous reinforcement learning algorithm based on improved parallel PSO, Springer. Appl Intell 49:4211\u20134222","DOI":"10.1007\/s10489-019-01487-4"},{"key":"10968_CR14","doi-asserted-by":"crossref","unstructured":"Duan Y, Cui BX, Xu XH (2011) A multi-agent reinforcement learning approach to robot soccer, Springer. Artif Intell 36:193\u2013211","DOI":"10.1007\/s10462-011-9244-8"},{"key":"10968_CR15","doi-asserted-by":"crossref","unstructured":"Fernando TG, Luis Javier Garcia V, Ana Lucila SO, Kim TH (2019) A comparison of learning methods over raw data: forecasting cab services market share in New York city, Springer. Multimed Tools Appl 78:29783\u201329804","DOI":"10.1007\/s11042-018-6285-x"},{"key":"10968_CR16","unstructured":"Guimaraes M, Santos P, Jhala A (2017) Prom week meet Skyrim: developing a social agent architecture in a commercial game. ACM, 17th\u00a0international conference on autonomous agent and multi-agent system, pp 1562\u20131564"},{"key":"10968_CR17","doi-asserted-by":"crossref","unstructured":"Hagelb\u00e4ck J (2016) Hybrid path finding in StarCraft. IEEE, Transactions on Computational Intelligence and AI in Games 38:319\u2013324","DOI":"10.1109\/TCIAIG.2015.2414447"},{"key":"10968_CR18","doi-asserted-by":"crossref","unstructured":"Hajuk M, Sukop M, Haun M (2019) Cognitive Multi-agent Systems, Book, Springer","DOI":"10.1007\/978-3-319-93687-1"},{"key":"10968_CR19","doi-asserted-by":"crossref","unstructured":"H\u00fcbner JF, Bordini RH (2010) Using agent-and organization-oriented programming to develop a team of agents for a competitive game. Springer, Science Business Media 59:351\u2013372","DOI":"10.1007\/s10472-010-9179-9"},{"key":"10968_CR20","doi-asserted-by":"crossref","unstructured":"Husseinzadeh Kashan A, Karimi B (2010) A new algorithm for constrained optimization inspired by the sport leagues championships. IEEE. Congress on evolutionary computation. https:\/\/ieeexplore.ieee.org\/document\/5586364","DOI":"10.1109\/CEC.2010.5586364"},{"key":"10968_CR21","doi-asserted-by":"crossref","unstructured":"Kamalapurkar R, Walters P, Rosenfeld DW (2018) Reinforcement learning for optimal feedback control. Springer","DOI":"10.1007\/978-3-319-78384-0"},{"key":"10968_CR22","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1080\/10798587.2000.10768155","volume":"6","author":"JH Kim","year":"2000","unstructured":"Kim JH, Vadakkepat P (2000) Multi-agent systems: a survey from the robot-soccer perspective. Intell Autom Soft Comput 6:3\u201317","journal-title":"Intell Autom Soft Comput"},{"key":"10968_CR23","doi-asserted-by":"crossref","unstructured":"Kobti Z, Sharma S (2007) A multi-agent architecture for game playing. Computational intelligence and games. Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games. https:\/\/ieeexplore.ieee.org\/document\/4219054","DOI":"10.1109\/CIG.2007.368109"},{"key":"10968_CR24","doi-asserted-by":"crossref","unstructured":"Koseler K, Stephan M (2018) Machine learning applications in baseball: a systematic literature review, applied artificial intelligence, applied artificial intelligence. Taylor & Francis, pp 745\u2013763","DOI":"10.1080\/08839514.2018.1442991"},{"key":"10968_CR25","unstructured":"Laffay HA (2011) Polo in the United States: a history. Book. MC Far Land & Company Inc"},{"key":"10968_CR26","unstructured":"Laffay HA (2014) Polo in Argentina: a history. MC Far Land & Company Inc"},{"key":"10968_CR27","unstructured":"Horace A Laffaye (2009) The evaluation of polo. McFarlane & Company Inc"},{"key":"10968_CR28","unstructured":"Lee JM, Lee BJ, Kim KE (2020) Reinforcement learning for control with multiple frequencies. NeurIPS. 34th\u00a0conference on neural information processing systems, pp 1\u201311"},{"key":"10968_CR29","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1504\/IJKESDP.2009.021982","volume":"1","author":"J Leng","year":"2009","unstructured":"Leng J, Lakhmi J (2009) Experimental analysis of eligibility traces strategies in temporal difference learning. Knowl Eng Soft Data Paradigms 1:26\u201339","journal-title":"Knowl Eng Soft Data Paradigms"},{"key":"10968_CR30","doi-asserted-by":"crossref","unstructured":"Leng J, Lim CP (2011) Reinforcement learning of competitive and cooperative skills in soccer agents. Elsevier. Appl Soft Comput 11:1353\u20131363","DOI":"10.1016\/j.asoc.2010.04.007"},{"key":"10968_CR31","doi-asserted-by":"crossref","unstructured":"Leng J, Fyfe C, Lakhmi J (2007) Reinforcement learning of competitive skills with soccer agents. Springer. Proc 11th Knowledge-Based Intell Inf Eng Syst 4692:572\u2013579","DOI":"10.1007\/978-3-540-74819-9_71"},{"key":"10968_CR32","doi-asserted-by":"crossref","unstructured":"Marinheiro J, Cardoso HL (2017) A generic agent architecture for cooperative multi-agent games. ICAART. Proceedings of the 9th International Conference on Agents and Artificial Intelligence 2:107-118","DOI":"10.5220\/0006253101070118"},{"key":"10968_CR33","doi-asserted-by":"crossref","unstructured":"Masoumi B, Meybodi MR (2010) Learning automata based multi-agent system algorithms for finding optimal policies in Markov games. J Control 14:137\u2013152","DOI":"10.1002\/asjc.315"},{"key":"10968_CR34","doi-asserted-by":"crossref","unstructured":"Masoumi B, Meybodi MR (2011) Speeding up learning automata based multi-agent the concept of Stigmergy and entropy. Elsevier. Expert Systems with Applications 38:8105\u20138118","DOI":"10.1016\/j.eswa.2010.12.152"},{"key":"10968_CR35","unstructured":"Masoumi B, Meybodi MR, Abtahi F (2012) Learning automata based algorithms for finding optimal policies in fully cooperative Markov games. PRZEGL\u0104D ELEKTROTECHNICZNY 8:280\u2013289"},{"key":"10968_CR36","doi-asserted-by":"crossref","unstructured":"Mattiassi ADA (2019) Fighting the game. Command systems and player-avatar interaction in fighting games in a social cognitive neuroscience framework. Springer. Multimedia Tools and Applications 78:13565\u201313591","DOI":"10.1007\/s11042-019-7231-2"},{"key":"10968_CR37","doi-asserted-by":"crossref","unstructured":"Mourao A, Magalhaes J (2013) Competitive affective gaming: winning with smile, proceedings of the 21st ACM international conference on multimedia, ACM, pp 83\u201391","DOI":"10.1145\/2502081.2502115"},{"key":"10968_CR38","doi-asserted-by":"crossref","unstructured":"Nandy A, Biswas M (2018) Reinforcement learning. Springer","DOI":"10.1007\/978-1-4842-3285-9"},{"key":"10968_CR39","doi-asserted-by":"crossref","unstructured":"Nash A, Koenig S (2013) Any-angle path planning. American Association for Artificial Intelligence. AI Magazine 34:85\u2013107","DOI":"10.1609\/aimag.v34i4.2512"},{"key":"10968_CR40","doi-asserted-by":"crossref","unstructured":"Parag C, Pendharkar (2012) Game theoretical applications for multi-agent systems. Elsevier. Expert Systems with Applications 39:273\u2013279","DOI":"10.1016\/j.eswa.2011.07.017"},{"key":"10968_CR41","doi-asserted-by":"crossref","unstructured":"Pelechano N, Fuentes C (2016) Hierarchical path-finding for navigation mesh. Elsevier. Computers Graphics 59:68\u201378","DOI":"10.1016\/j.cag.2016.05.023"},{"key":"10968_CR42","doi-asserted-by":"crossref","unstructured":"Polk S, Oommen BJ (2018) Novel threat-based AI strategies that incorporate adaptive data structures for multi-player board game. Springer. Applied Intelligence 48:1893\u20131911","DOI":"10.1007\/s10489-016-0835-6"},{"key":"10968_CR43","unstructured":"Polo Federation of Iran site: (n.d.)\u00a0http:\/\/iranPolo.org\/?page_id=1521#lightbox[gallery-1]\/1\/"},{"key":"10968_CR44","unstructured":"Rabin S (2002) AI programming WISDOM. Charles River media. April 3"},{"key":"10968_CR45","doi-asserted-by":"crossref","unstructured":"Scheepers C, Engelbrecht AP (2014) Competitive co-evolutionary training of simple soccer agents from zero knowledge. IEEE. Congress on Evolutionary Computation. https:\/\/ieeexplore.ieee.org\/document\/6900236","DOI":"10.1109\/CEC.2014.6900236"},{"key":"10968_CR46","doi-asserted-by":"crossref","unstructured":"Scheepers C, Engelbrecht AP (2014) Training multi-agent teams from zero knowledge with the competitive co-evolutionary team-based particle swarm optimizer. Springer. Soft Compute 20:607\u2013620","DOI":"10.1007\/s00500-014-1525-0"},{"key":"10968_CR47","doi-asserted-by":"crossref","unstructured":"Scheepers C, Engelbrecht AP (2014) Analysis of stagnation behavior of competitive co-evolutionary trained neuro-controller. IEEE. Symposium on Swarm Intelligence. https:\/\/ieeexplore.ieee.org\/document\/7011795","DOI":"10.1109\/SIS.2014.7011795"},{"key":"10968_CR48","doi-asserted-by":"crossref","unstructured":"Sewak M (2019) Deep reinforcement learning. Springer","DOI":"10.1007\/978-981-13-8285-7"},{"key":"10968_CR49","doi-asserted-by":"crossref","unstructured":"Stone P, Veloso M (1998) Layered approach to learning client behaviors in the Robocup. Taylor & Francis. Applied Artificial Intelligence 12:165\u2013188","DOI":"10.1080\/088395198117811"},{"key":"10968_CR50","doi-asserted-by":"crossref","unstructured":"Sun P, Hu Y, Lan J, Tian L, Chen M (2019) TIDE: time-relevant deep reinforcement learning for routing optimization. Elsevier. Future Generation Computer Systems 99:401\u2013409","DOI":"10.1016\/j.future.2019.04.014"},{"key":"10968_CR51","doi-asserted-by":"crossref","unstructured":"Tomaz L.B.P, Julia R.M.S, Duarte V.A (2017) A multi-agent player system composed by expert agents in specific game stages operating in high performance environment. Springer. Applied Intelligence 48:1\u201322","DOI":"10.1007\/s10489-017-0952-x"},{"key":"10968_CR52","doi-asserted-by":"crossref","unstructured":"Weyns D, Mascarsdi V, Ricci A (2019) Engineering multi-agent systems. Springer","DOI":"10.1007\/978-3-030-25693-7"},{"key":"10968_CR53","unstructured":"Wooldridge M (2002) An introduction to multi-agent systems. John Wiley& Sons. August"},{"key":"10968_CR54","doi-asserted-by":"crossref","unstructured":"Wooldridge M, Mller J, Tambe M (1997) Intelligent Agent II \u2013Agent Theories. Architecture and Languages. Springer","DOI":"10.1007\/3540608052_81"},{"key":"10968_CR55","doi-asserted-by":"crossref","unstructured":"Yu FR, He Y (2019) Deep reinforcement learning for wireless networks. Springer","DOI":"10.1007\/978-3-030-10546-4"},{"key":"10968_CR56","doi-asserted-by":"crossref","unstructured":"Yuan Y, Yu Z.L, Gu Z, Deng X, Li X (2019) A novel multi-step reinforcement learning method for solving reward hacking. Springer. Applied Intelligence 49:2878\u20132888","DOI":"10.1007\/s10489-019-01417-4"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10968-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-10968-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10968-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:56:35Z","timestamp":1672084595000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-10968-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,9]]},"references-count":56,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["10968"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-10968-z","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,9]]},"assertion":[{"value":"9 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}