{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:48:18Z","timestamp":1729666098312,"version":"3.28.0"},"reference-count":11,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010619","type":"proceedings-article","created":{"date-parts":[[2015,1,19]],"date-time":"2015-01-19T21:48:03Z","timestamp":1421704083000},"page":"1-8","source":"Crossref","is-referenced-by-count":8,"title":["Annealing-pareto multi-objective multi-armed bandit algorithm"],"prefix":"10.1109","author":[{"given":"Saba Q.","family":"Yahyaa","sequence":"first","affiliation":[]},{"given":"Madalina M.","family":"Drugan","sequence":"additional","affiliation":[]},{"given":"Bernard","family":"Manderick","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2003.810758"},{"journal-title":"Statistical Mechanics Entropy Order Parameters and Complexity","year":"2006","author":"sethna","key":"ref3"},{"key":"ref10","article-title":"An Empirical Evaluation of Thompson Sampling","author":"chapelle","year":"2011","journal-title":"Proc Advances in Neural Information Processing Systems (NIPS'11)"},{"key":"ref6","article-title":"Knowledge Gradient for Multi-Objective Multi-Armed Bandit Algorithms","author":"yahyaa","year":"2014","journal-title":"Proc International Conference on Agents and Artificial Intelligence (ICAART'14)"},{"key":"ref11","first-page":"2249","article-title":"Analysis of Thompson Sampling for the Multi-armed Bandit Problem","volume":"23","author":"agrawal","year":"2012","journal-title":"Proc and Work Annual Conference on Learning Theory (COLT'12)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"ref7","article-title":"The Knowledge Gradient Policy for a General Class of Online Learning Problems","author":"ryzhov","year":"2011","journal-title":"Operation Research"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2013.6707036"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.1002\/9781118309858","author":"powell","year":"2012","journal-title":"Optimal Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889390"}],"event":{"name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","start":{"date-parts":[[2014,12,9]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2014,12,12]]}},"container-title":["2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7000183\/7010603\/07010619.pdf?arnumber=7010619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T23:55:01Z","timestamp":1498175701000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010619","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}