{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:50:22Z","timestamp":1729677022184,"version":"3.28.0"},"reference-count":23,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,8]]},"DOI":"10.1109\/cig.2011.6031994","type":"proceedings-article","created":{"date-parts":[[2011,10,5]],"date-time":"2011-10-05T10:19:54Z","timestamp":1317809994000},"page":"95-101","source":"Crossref","is-referenced-by-count":4,"title":["Reinforcement learning for the soccer dribbling task"],"prefix":"10.1109","author":[{"given":"Arthur","family":"Carvalho","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renato","family":"Oliveira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/978-3-642-02921-9_6","article-title":"A case study on improving defense behavior in soccer simulation 2D: The neurohassle approach","author":"gabel","year":"2009","journal-title":"RoboCup 2008 Robot Soccer World Cup XII"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.973373"},{"key":"17","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1007\/978-3-540-25940-4_52","article-title":"A fuzzy reinforcement learning for a ball interception problem","author":"nakashima","year":"2004","journal-title":"RoboCup 2003 Robot Soccer World Cup VII"},{"key":"23","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proceedings of the 16th International Conference on Machine Learning"},{"key":"18","first-page":"1341","article-title":"A new perspective to the keepaway soccer: The takers","author":"iscen","year":"2008","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"15","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1007\/3-540-64473-3_74","article-title":"Refinement of soccer agents' positions using reinforcement learning","author":"andou","year":"1998","journal-title":"Lecture Notes in Computer Science"},{"key":"16","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1007\/3-540-45324-5_40","article-title":"Karlsruhe brainstormers - A reinforcement learning approach to robotic soccer","author":"riedmiller","year":"2001","journal-title":"Lecture Notes in Computer Science"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1177\/105971230501300301"},{"journal-title":"UNH CMAC Version 2 1 The University of New Hampshire Implementation of the Cerebellar Model Arithmetic Computer - CMAC","year":"1994","author":"miller","key":"14"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/0025-5564(71)90051-4"},{"key":"12","article-title":"Brain, behavior, and robotics","author":"albus","year":"1981","journal-title":"BYTE Books"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2008.4543536"},{"key":"3","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","volume":"8","author":"sutton","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74024-7_7"},{"key":"2","first-page":"1040","article-title":"Reinforcement learning with function approximation converges to a region","volume":"13","author":"gordon","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1080\/088395198117848"},{"journal-title":"Dynamic Programming","year":"2003","author":"bellman","key":"10"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"7"},{"journal-title":"Users manual RoboCup soccer server manual for soccer server version 7 07 and later","year":"2003","author":"chen","key":"6"},{"key":"5","first-page":"1595","article-title":"A convergent form of approximate policy iteration","volume":"15","author":"perkins","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","year":"2005","author":"puterman","key":"9"},{"journal-title":"The Incremental Development of a Synthetic Multi-agent System The UvA Trilearn 2001 Robotic Soccer Simulation Team","year":"2002","author":"de boer","key":"8"}],"event":{"name":"2011 IEEE Conference on Computational Intelligence and Games (CIG)","start":{"date-parts":[[2011,8,31]]},"location":"Seoul, Korea (South)","end":{"date-parts":[[2011,9,3]]}},"container-title":["2011 IEEE Conference on Computational Intelligence and Games (CIG'11)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6026199\/6031971\/06031994.pdf?arnumber=6031994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T03:31:03Z","timestamp":1497929463000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6031994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cig.2011.6031994","relation":{},"subject":[],"published":{"date-parts":[[2011,8]]}}}