{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T07:23:27Z","timestamp":1778570607023,"version":"3.51.4"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,11,9]],"date-time":"2020-11-09T00:00:00Z","timestamp":1604880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,9]],"date-time":"2020-11-09T00:00:00Z","timestamp":1604880000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,9]],"date-time":"2020-11-09T00:00:00Z","timestamp":1604880000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002322","name":"CAPES","doi-asserted-by":"publisher","award":["88882.161989\/2017-01"],"award-info":[{"award-number":["88882.161989\/2017-01"]}],"id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003593","name":"CNPq - National Research Council of Brasil","doi-asserted-by":"publisher","award":["304134\/2-18-0"],"award-info":[{"award-number":["304134\/2-18-0"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,11,9]]},"DOI":"10.1109\/lars\/sbr\/wre51543.2020.9307084","type":"proceedings-article","created":{"date-parts":[[2021,1,8]],"date-time":"2021-01-08T02:28:28Z","timestamp":1610072908000},"page":"1-6","source":"Crossref","is-referenced-by-count":15,"title":["Deep Reinforcement Learning for Humanoid Robot Dribbling"],"prefix":"10.1109","author":[{"given":"Alexandre F. V.","family":"Muzio","sequence":"first","affiliation":[{"name":"Aeronautics Institute of Technology, Pra\u00e7a Marechal Eduardo Gomes,Autonomous Computational Systems Lab (LAB-SCA), Computer Science Division,S\u00e0o Jos\u00e9 dos Campos,SP,Brazil,12228-900"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcos R.O. A.","family":"Maximo","sequence":"additional","affiliation":[{"name":"Aeronautics Institute of Technology, Pra\u00e7a Marechal Eduardo Gomes,Autonomous Computational Systems Lab (LAB-SCA), Computer Science Division,S\u00e0o Jos\u00e9 dos Campos,SP,Brazil,12228-900"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Yoneyama","sequence":"additional","affiliation":[{"name":"Aeronautics Institute of Technology, Pra\u00e7a Marechal Eduardo Gomes,Electronic Engineering Division,S\u00e0o Jos\u00e9 dos Campos,SP,Brazil,12228-900"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Continuous adaptation via meta-learning in nonstationary and competitive environments","volume":"abs 1710 3641","author":"al-shedivat","year":"2017","journal-title":"CoRR"},{"key":"ref32","article-title":"Benchmarking deep reinforcement learning for continuous control","volume":"abs 1604 6778","author":"duan","year":"2016","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref30","author":"stoecker","year":"2011","journal-title":"Roboviz"},{"key":"ref10","article-title":"A study of layered learning strategies applied to individual behaviors in robot soccer","author":"leottau","year":"2016","journal-title":"RoboCup 2015 Robot World Cup XIX ser Lecture Notes in Artificial Intelligence"},{"key":"ref11","article-title":"Design and optimization of an omnidirectional humanoid walk: A winning approach at the RoboCup 2011 3D simulation competition","author":"macalpine","year":"2012","journal-title":"Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2017.09.001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/106365603321828970"},{"key":"ref14","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","volume":"abs 1703 3864","author":"salimans","year":"2017","journal-title":"CoRR"},{"key":"ref15","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref16","article-title":"Continuous control with deep reinforcement learning","volume":"abs 1509 2971","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref17","author":"wiliams","year":"1992","journal-title":"Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning"},{"key":"ref18","article-title":"Asynchronous methods for deep reinforcement learning","volume":"abs 1602 1783","author":"mnih","year":"2016","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.973365"},{"key":"ref4","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref27","author":"maximo","year":"2015","journal-title":"Omnidirectional ZMP-Based Walking for a Humanoid Robot"},{"key":"ref3","article-title":"Trust region policy optimization","volume":"abs 1502 5477","author":"schulman","year":"2015","journal-title":"CoRR"},{"key":"ref6","article-title":"Deep reinforcement learning in parameterized action space","author":"hausknecht","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref29","author":"dhariwal","year":"2017","journal-title":"OpenAI Baselines"},{"key":"ref5","first-page":"61","author":"gabel","year":"2009","journal-title":"A Case Study on Improving Defense Behavior in Soccer Simulation 2D The NeuroHassle Approach"},{"key":"ref8","author":"schwab","year":"2020","journal-title":"Robot deep reinforcement learning Tensor state-action spaces and auxiliary task learning with multiple state representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PlatCon.2018.8472776"},{"key":"ref2","first-page":"-387i","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"0","journal-title":"Proceedings of the 31st International Conference on International Conference on Machine Learning - Volume 32 ser ICML'14 JMLR org"},{"key":"ref9","author":"leottau","year":"2014","journal-title":"Ball dribbling for humanoid biped robots A reinforcement learning and fuzzy control approach"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref20","article-title":"Teacher-student curriculum learning","volume":"abs 1707 183","author":"matiisen","year":"2017","journal-title":"CoRR"},{"key":"ref22","year":"2004","journal-title":"Simspark"},{"key":"ref21","article-title":"Emergent complexity via multi-agent competition","volume":"abs 1710 3748","author":"bansal","year":"2017","journal-title":"CoRR"},{"key":"ref24","author":"robotics","year":"2018","journal-title":"Nao robot"},{"key":"ref23","year":"2004","journal-title":"Open Dynamics Engine (ODE)"},{"key":"ref26","author":"muzio","year":"2016","journal-title":"Itandroids soccer3d team description paper 2016"},{"key":"ref25","author":"melo","year":"2017","journal-title":"Itandroids soccer3d team description paper 2017"}],"event":{"name":"2020 Latin American Robotics Symposium (LARS), 2020 Brazilian Symposium on Robotics (SBR) and 2020 Workshop on Robotics in Education (WRE)","location":"Natal, Brazil","start":{"date-parts":[[2020,11,9]]},"end":{"date-parts":[[2020,11,13]]}},"container-title":["2020 Latin American Robotics Symposium (LARS), 2020 Brazilian Symposium on Robotics (SBR) and 2020 Workshop on Robotics in Education (WRE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9306854\/9306930\/09307084.pdf?arnumber=9307084","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:57:09Z","timestamp":1656453429000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9307084\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,9]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/lars\/sbr\/wre51543.2020.9307084","relation":{},"subject":[],"published":{"date-parts":[[2020,11,9]]}}}