{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:40:09Z","timestamp":1755909609842,"version":"3.44.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2008,5,1]],"date-time":"2008-05-01T00:00:00Z","timestamp":1209600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2008,5,1]],"date-time":"2008-05-01T00:00:00Z","timestamp":1209600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,5]]},"DOI":"10.1109\/robot.2008.4543717","type":"proceedings-article","created":{"date-parts":[[2008,6,16]],"date-time":"2008-06-16T14:43:38Z","timestamp":1213627418000},"page":"3321-3327","source":"Crossref","is-referenced-by-count":5,"title":["Reinforcement learning with function approximation for cooperative navigation tasks"],"prefix":"10.1109","author":[{"given":"Francisco S.","family":"Melo","sequence":"first","affiliation":[{"name":"Institute for Systems and Robotics, Instituto Superior T\u00e9cnico Lisboa, Portugal"}]},{"given":"M. Isabel","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"Institute for Systems and Robotics, Instituto Superior T\u00e9cnico Lisboa, Portugal"}]}],"member":"263","reference":[{"key":"19","article-title":"social structures and the problem of coordination in intelligent agent societies","author":"findler","year":"2000","journal-title":"Agent-Based Simulation Planning and Control Session IMACS World Congress"},{"key":"17","first-page":"535","article-title":"an algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proc 17th Int Conf Machine Learning"},{"key":"18","first-page":"1334","article-title":"hierarchical reinforcement learning in communication-mediated multiagent coordination","author":"fischer","year":"2004","journal-title":"Proc 3rd Int Joint Conf Autonomous Agents and Multiagent Systems"},{"article-title":"learning from delayed rewards","year":"1989","author":"watkins","key":"15"},{"journal-title":"Measure Theory","year":"1974","author":"halmos","key":"16"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1095"},{"key":"14","first-page":"195","article-title":"planning, learning and coordination in multiagent decision processes","author":"boutilier","year":"1996","journal-title":"Proc 6th Conf Theoretical Aspects of Rationality and Knowledge"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-3267-7"},{"key":"12","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"21","article-title":"learning to coordinate in topological navigation tasks","author":"melo","year":"2007","journal-title":"Proc 6th IFAC Symp Intelligent Autonomous Vehicles"},{"key":"20","first-page":"1571","article-title":"reinforcement learning to play an optimal nash equilibrium in team markov games","volume":"15","author":"wang","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-4149(98)00029-5"},{"article-title":"reinforcement learning in coordinated navigation tasks","year":"2007","author":"melo","key":"24"},{"key":"25","first-page":"1023","article-title":"acting optimally in partially observable stochastic domains","author":"cassandra","year":"1994","journal-title":"Proc 12th Nat Conf Artificial Intelligence"},{"article-title":"markov localization: a probabilistic framework for mobile robot localization and navigation","year":"1998","author":"fox","key":"26"},{"article-title":"exact and approximate algorithms for partially observable markov decision processes","year":"1998","author":"cassandra","key":"27"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1039"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"10","first-page":"46","article-title":"an approach to noncommunicative multiagent coordination in continuous domains","author":"kok","year":"2002","journal-title":"Proc 12th Belgian-Dutch Conf Machine Learning"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"1"},{"year":"0","key":"7"},{"key":"6","article-title":"coordinated reinforcement learning","author":"guestrin","year":"2002","journal-title":"Proc 19th Int Conf Machine Learning"},{"key":"5","first-page":"746","article-title":"the dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proc 15th Nat Conf Artificial Intelligence (AAAI'98)"},{"key":"4","article-title":"sequential optimality and coordination in multiagent systems","author":"boutilier","year":"1999","journal-title":"Proc 16th Int Joint Conf Artificial Intelligence"},{"key":"9","article-title":"emerging coordination in infinite team markov games","author":"melo","year":"2008","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"year":"0","key":"8"}],"event":{"name":"2008 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2008,5,19]]},"location":"Pasadena, CA, USA","end":{"date-parts":[[2008,5,23]]}},"container-title":["2008 IEEE International Conference on Robotics and Automation"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4534525\/4543169\/04543717.pdf?arnumber=4543717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:01:44Z","timestamp":1755907304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/4543717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,5]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/robot.2008.4543717","relation":{},"subject":[],"published":{"date-parts":[[2008,5]]}}}