{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:05:26Z","timestamp":1743026726892,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030275433"},{"type":"electronic","value":"9783030275440"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-27544-0_27","type":"book-chapter","created":{"date-parts":[[2019,8,5]],"date-time":"2019-08-05T23:06:44Z","timestamp":1565046404000},"page":"324-336","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Adjusted Bounded Weighted Policy Learner"],"prefix":"10.1007","author":[{"given":"David","family":"Sim\u00f5es","sequence":"first","affiliation":[]},{"given":"Nuno","family":"Lau","sequence":"additional","affiliation":[]},{"given":"Lu\u00eds Paulo","family":"Reis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,4]]},"reference":[{"key":"27_CR1","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1613\/jair.2628","volume":"33","author":"S Abdallah","year":"2008","unstructured":"Abdallah, S., Lesser, V.: A multiagent reinforcement learning algorithm with non-linear dynamics. J. Artif. Intell. Res. 33, 521\u2013549 (2008)","journal-title":"J. Artif. Intell. Res."},{"key":"27_CR2","first-page":"1","volume-title":"The New Palgrave Dictionary of Economics","author":"R.J. Aumann","year":"2008","unstructured":"Aumann, R.J.: Game Theory. The New Palgrave Dictionary of Economics, pp. 1\u201340 (2017)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Awheda, M.D., Schwartz, H.M.: Exponential moving average q-learning algorithm. In: 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), pp. 31\u201338, April 2013","DOI":"10.1109\/ADPRL.2013.6614986"},{"issue":"3","key":"27_CR4","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1007\/s10458-007-9013-x","volume":"15","author":"B Banerjee","year":"2007","unstructured":"Banerjee, B., Peng, J.: Generalized multiagent learning with performance bound. Auton. Agent. Multi-Agent Syst. 15(3), 281\u2013312 (2007)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"issue":"2","key":"27_CR5","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1109\/TCYB.2013.2253094","volume":"44","author":"RA Bianchi","year":"2014","unstructured":"Bianchi, R.A., Martins, M.F., Ribeiro, C.H., Costa, A.H.: Heuristically-accelerated multiagent reinforcement learning. IEEE Trans. Cybern. 44(2), 252\u2013265 (2014)","journal-title":"IEEE Trans. Cybern."},{"key":"27_CR6","unstructured":"Bowling, M.: Convergence and no-regret in multiagent learning. In: Proceedings of the 17th International Conference on Neural Information Processing Systems, NIPS 2004, pp. 209\u2013216. MIT Press, Cambridge (2004)"},{"issue":"2","key":"27_CR7","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M Bowling","year":"2002","unstructured":"Bowling, M., Veloso, M.: Multiagent learning using a variable learning rate. Artif. Intell. 136(2), 215\u2013250 (2002)","journal-title":"Artif. Intell."},{"issue":"1\u20132","key":"27_CR8","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10994-006-0143-1","volume":"67","author":"V Conitzer","year":"2007","unstructured":"Conitzer, V., Sandholm, T.: Awesome: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents. Mach. Learn. 67(1\u20132), 23\u201343 (2007)","journal-title":"Mach. Learn."},{"key":"27_CR9","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1007\/978-3-662-43505-2_44","volume-title":"Springer Handbook of Computational Intelligence","author":"N Hansen","year":"2015","unstructured":"Hansen, N., Arnold, D.V., Auger, A.: Evolution strategies. In: Kacprzyk, J., Pedrycz, W. (eds.) Springer Handbook of Computational Intelligence, pp. 871\u2013898. Springer, Heidelberg (2015). https:\/\/doi.org\/10.1007\/978-3-662-43505-2_44"},{"issue":"Nov","key":"27_CR10","first-page":"1039","volume":"4","author":"J Hu","year":"2003","unstructured":"Hu, J., Wellman, M.P.: Nash q-learning for general-sum stochastic games. J. Mach. Learn. Res. 4(Nov), 1039\u20131069 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"27_CR11","unstructured":"Kaisers, M., Tuyls, K.: Frequency adjusted multi-agent q-learning. In: Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems, vol. 1, pp. 309\u2013316. International Foundation for Autonomous Agents and Multiagent Systems (2010)"},{"key":"27_CR12","volume-title":"Artificial Intelligence: A Modern Approach","author":"SJ Russell","year":"2016","unstructured":"Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach. Pearson Education Limited, Malaysia (2016)"},{"key":"27_CR13","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1007\/978-3-319-70836-2_11","volume-title":"ROBOT 2017: Third Iberian Robotics Conference","author":"D Sim\u00f5es","year":"2018","unstructured":"Sim\u00f5es, D., Lau, N., Reis, L.P.: Mixed-policy asynchronous deep q-learning. In: Ollero, A., Sanfeliu, A., Montano, L., Lau, N., Cardeira, C. (eds.) ROBOT 2017. AISC, vol. 694, pp. 129\u2013140. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-70836-2_11"},{"key":"27_CR14","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.enconman.2015.06.030","volume":"103","author":"L Xi","year":"2015","unstructured":"Xi, L., Yu, T., Yang, B., Zhang, X.: A novel multi-agent decentralized win or learn fast policy hill-climbing with eligibility trace algorithm for smart generation control of interconnected complex power grids. Energy Convers. Manag. 103, 82\u201393 (2015)","journal-title":"Energy Convers. Manag."},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, C., Lesser, V.: Multi-agent learning with policy prediction. In: Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence, AAAI 2010, pp. 927\u2013934. AAAI Press (2010)","DOI":"10.1609\/aaai.v24i1.7639"},{"issue":"6","key":"27_CR16","doi-asserted-by":"publisher","first-page":"1367","DOI":"10.1109\/TCYB.2016.2544866","volume":"47","author":"Z Zhang","year":"2017","unstructured":"Zhang, Z., Zhao, D., Gao, J., Wang, D., Dai, Y.: FMRQ\u2013a multiagent reinforcement learning algorithm for fully cooperative tasks. IEEE Trans. Cybern. 47(6), 1367\u20131379 (2017)","journal-title":"IEEE Trans. Cybern."}],"container-title":["Lecture Notes in Computer Science","RoboCup 2018: Robot World Cup XXII"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-27544-0_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,6]],"date-time":"2023-08-06T00:05:07Z","timestamp":1691280307000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-27544-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030275433","9783030275440"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-27544-0_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"4 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RoboCup","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Robot World Cup","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Montr\u00e9al, QC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"robocup2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.robocup2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}