{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T13:47:21Z","timestamp":1725716841230},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,11]]},"DOI":"10.1109\/devlrn.2012.6400862","type":"proceedings-article","created":{"date-parts":[[2013,1,7]],"date-time":"2013-01-07T16:36:02Z","timestamp":1357576562000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["Optimal rewards in multiagent teams"],"prefix":"10.1109","author":[{"given":"Bingyao","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satinder","family":"Singh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard L.","family":"Lewis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyin","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","article-title":"A 'neural' network that learns to play backgammon","author":"tesauro","year":"1987","journal-title":"Neural Information Processing Systems"},{"key":"17","article-title":"Internal rewards mitigate agent boundedness","author":"sorg","year":"0","journal-title":"International Conference on Machine Learning 2010"},{"key":"18","article-title":"Optimal rewards versus leaf-evaluation heuristics in planning agents","author":"sorg","year":"0","journal-title":"Proceedings of Twenty-Fifth AAAI Conference on Artificial Intelligence 2011"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2011.6037325"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051031"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.170605"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.1999.785467"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"12","article-title":"An MDP-Based approach to Online Mechanism Design","author":"parkes","year":"0","journal-title":"Proc 17th Annual Conf on Neural Information Processing Systems 2003"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1209\/epl\/i2000-00208-x"},{"key":"3","article-title":"Strong mitigation: Nesting search for good policies within search for good reward","author":"bratman","year":"0","journal-title":"International Conference on Autonomous Agents and Multiagent Systems 2012"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2007.4354030"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"1","first-page":"12","article-title":"Robot learning from demonstration","author":"atkeson","year":"1997","journal-title":"Proc Fourteenth Int Conf Machine Learning"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.12.006.2007"},{"key":"7","article-title":"Bandit based Monte-Carlo planning","author":"kocsis","year":"0","journal-title":"Proceedings of the European Conference on Machine Learning 2006"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2010.936952"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1145\/1538788.1538812"},{"key":"4","article-title":"Making rational decisions using adaptive utility elicitation","author":"chajewska","year":"0","journal-title":"Proc the 2000 National Conference on Artificial Intelligence"},{"key":"9","article-title":"Algorithms for inverse reinforcement learning","author":"ng","year":"0","journal-title":"International Conference on Machine Learning 2000"},{"key":"8","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"0","journal-title":"Proceedings of International Conference on Machine Learning 1999"}],"event":{"name":"2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)","start":{"date-parts":[[2012,11,7]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2012,11,9]]}},"container-title":["2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6384412\/6400572\/06400862.pdf?arnumber=6400862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,22]],"date-time":"2017-03-22T12:33:05Z","timestamp":1490185985000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6400862\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/devlrn.2012.6400862","relation":{},"subject":[],"published":{"date-parts":[[2012,11]]}}}