{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T15:43:11Z","timestamp":1745509391709,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030361495"},{"type":"electronic","value":"9783030361501"}],"license":[{"start":{"date-parts":[[2019,11,20]],"date-time":"2019-11-20T00:00:00Z","timestamp":1574208000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-36150-1_44","type":"book-chapter","created":{"date-parts":[[2019,11,19]],"date-time":"2019-11-19T14:03:59Z","timestamp":1574172239000},"page":"537-548","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Learning Low-Level Behaviors and High-Level Strategies in Humanoid Soccer"],"prefix":"10.1007","author":[{"given":"David","family":"Sim\u00f5es","sequence":"first","affiliation":[]},{"given":"Pedro","family":"Amaro","sequence":"additional","affiliation":[]},{"given":"Tiago","family":"Silva","sequence":"additional","affiliation":[]},{"given":"Nuno","family":"Lau","sequence":"additional","affiliation":[]},{"given":"Lu\u00eds Paulo","family":"Reis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,20]]},"reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Abdolmaleki, A., Lau, N., Reis, L.P., Neumann, G.: Regularized covariance estimation for weighted maximum likelihood policy search methods. In: 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pp. 154\u2013159. IEEE (2015)","DOI":"10.1109\/HUMANOIDS.2015.7363529"},{"key":"44_CR2","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1007\/978-3-319-68792-6_4","volume-title":"RoboCup 2016: Robot World Cup XX","author":"Abbas Abdolmaleki","year":"2017","unstructured":"Abdolmaleki, A., Sim\u00f5es, D., Lau, N., Reis, L.P., Neumann, G.: Learning a humanoid kick with controlled distance. In: Robot World Cup, pp. 45\u201357. Springer, Hedidelberg (2016)"},{"key":"44_CR3","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/978-3-642-34654-5_50","volume-title":"Advances in Artificial Intelligence - IBERAMIA 2012","author":"L Cruz","year":"2012","unstructured":"Cruz, L., Reis, L.P., Lau, N., Sousa, A.: Optimization approach for the development of humanoid robots\u2019 behaviors. In: Pav\u00f3n, J., Duque-M\u00e9ndez, N.D., Fuentes-Fern\u00e1ndez, R. (eds.) Advances in Artificial Intelligence - IBERAMIA 2012, pp. 491\u2013500. Springer, Heidelberg (2012)"},{"key":"44_CR4","unstructured":"Federation, R.: Robocup simulation 3d league rules. https:\/\/ssim.robocup.org\/wp-content\/uploads\/2018\/12\/Rules_RoboCupSim3D2018.pdf . Accessed 21 Apr 2019"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Foerster, J.N., Farquhar, G., Afouras, T., Nardelli, N., Whiteson, S.: Counterfactual multi-agent policy gradients. CoRR abs\/1705.08926 (2017)","DOI":"10.1609\/aaai.v32i1.11794"},{"issue":"1","key":"44_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/106365603321828970","volume":"11","author":"N Hansen","year":"2003","unstructured":"Hansen, N., M\u00fcller, S.D., Koumoutsakos, P.: Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (CMA-ES). Evol. Comput. 11(1), 1\u201318 (2003)","journal-title":"Evol. Comput."},{"key":"44_CR7","unstructured":"Hansen, N.: The CMA evolution strategy: a tutorial. arXiv preprint arXiv:1604.00772 (2016)"},{"key":"44_CR8","first-page":"743","volume-title":"ROBOT 2017: Third Iberian Robotics Conference","author":"S. Mohammadreza Kasaei","year":"2017","unstructured":"Kasaei, S.M., Sim\u00f5es, D., Lau, N., Pereira, A.: A hybrid zmp-cpg based walk engine for biped robots. In: Iberian Robotics Conference, pp. 743\u2013755. Springer, Heidelberg (2017)"},{"key":"44_CR9","unstructured":"Kupcsik, A., Deisenroth, M., Peters, J., Neumann, G.: Data-efficient contextual policy search for robot movement skills. In: Proceedings of the National Conference on Artificial Intelligence (AAAI) (2013)"},{"key":"44_CR10","unstructured":"Lau, N., Reis, L.P., Shafii, N., Ferreira, R., Abdolmaleki, A.: FC Portugal 3D simulation team: team description paper. RoboCup 2013 (2013)"},{"key":"44_CR11","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. CoRR abs\/1706.02275 (2017)"},{"key":"44_CR12","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.artint.2017.09.001","volume":"254","author":"P MacAlpine","year":"2018","unstructured":"MacAlpine, P., Stone, P.: Overlapping layered learning. Artif. Intell. 254, 21\u201343 (2018)","journal-title":"Artif. Intell."},{"key":"44_CR13","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807\u2013814 (2010)"},{"key":"44_CR14","unstructured":"Peng, P., Yuan, Q., Wen, Y., Yang, Y., Tang, Z., Long, H., Wang, J.: Multiagent bidirectionally-coordinated nets for learning to play starcraft combat games. CoRR abs\/1703.10069 (2017)"},{"key":"44_CR15","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1007\/978-3-642-02478-8_101","volume-title":"Bio-Inspired Systems: Computational and Ambient Intelligence","author":"H Picado","year":"2009","unstructured":"Picado, H., Gestal, M., Lau, N., Reis, L.P., Tom\u00e9, A.M.: Automatic generation of biped walk behavior using genetic algorithms. In: Cabestany, J., Sandoval, F., Prieto, A., Corchado, J.M. (eds.) Bio-Inspired Systems: Computational and Ambient Intelligence, pp. 805\u2013812. Springer, Heidelberg (2009)"},{"key":"44_CR16","doi-asserted-by":"crossref","unstructured":"R\u00fcckstie\u00df, T., Felder, M., Schmidhuber, J.: State-dependent exploration for policy gradient methods. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 234\u2013249. Springer, Heidelberg (2008)","DOI":"10.1007\/978-3-540-87481-2_16"},{"key":"44_CR17","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"44_CR18","first-page":"3","volume-title":"Advances in Intelligent Systems and Computing","author":"David Sim\u00f5es","year":"2019","unstructured":"Sim\u00f5es, D., Lau, N., Reis, L.P.: Multi-agent neural reinforcement-learning system with communication. In: World Conference on Information Systems and Technologies, pp. 3\u201312. Springer, Heidelberg (2019)"},{"key":"44_CR19","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/3-540-45327-X_42","volume-title":"RoboCup-99: Robot Soccer World Cup III","author":"Peter Stone","year":"2000","unstructured":"Stone, P., Veloso, M.: Layered learning and flexible teamwork in RoboCup simulation agents. In: Robot Soccer World Cup, pp. 495\u2013508. Springer, Heidelberg (1999)"},{"key":"44_CR20","unstructured":"Stulp, F., Sigaud, O.: Path integral policy improvement with covariance matrix adaptation. arXiv preprint arXiv:1206.4621 (2012)"},{"key":"44_CR21","unstructured":"Sukhbaatar, S., Szlam, A., Fergus, R.: Learning multiagent communication with backpropagation. CoRR abs\/1605.07736 (2016)"},{"key":"44_CR22","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wierstra, D., Schaul, T., Schmidhuber, J.: Efficient natural evolution strategies. In: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation, pp. 539\u2013546. ACM (2009)","DOI":"10.1145\/1569901.1569976"},{"issue":"Nov","key":"44_CR23","first-page":"3137","volume":"11","author":"E Theodorou","year":"2010","unstructured":"Theodorou, E., Buchli, J., Schaal, S.: A generalized path integral control approach to reinforcement learning. J. Mach. Learn. Res. 11(Nov), 3137\u20133181 (2010)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"44_CR24","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","journal-title":"Mach. Learn."}],"container-title":["Advances in Intelligent Systems and Computing","Robot 2019: Fourth Iberian Robotics Conference"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-36150-1_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T03:55:32Z","timestamp":1665028532000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-36150-1_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,20]]},"ISBN":["9783030361495","9783030361501"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-36150-1_44","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2019,11,20]]},"assertion":[{"value":"20 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ROBOT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iberian Robotics conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"robot2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}