{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T21:03:26Z","timestamp":1729631006637,"version":"3.28.0"},"reference-count":25,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010646","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":2,"title":["Tunable and generic problem instance generation for multi-objective reinforcement learning"],"prefix":"10.1109","author":[{"given":"Deon","family":"Garrett","sequence":"first","affiliation":[]},{"given":"Jordi","family":"Bieger","sequence":"additional","affiliation":[]},{"given":"Kristinn R.","family":"Thorisson","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"197","article-title":"Multi-criteria reinforcement learning","author":"g\u00e1bor","year":"1998","journal-title":"Fifteenth International Conference on Machine Learning"},{"key":"ref11","article-title":"Dynamic survey of graph labeling","volume":"14","author":"gallian","year":"2007","journal-title":"Electronic Journal of Combinatorics"},{"journal-title":"In Proceedings of the Third International Conference on Computational Sustainability","article-title":"Managing invasive species in a river network","year":"2012","author":"hall","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/0012-365X(73)90067-8"},{"journal-title":"Learning to Solve Multiple Goals","year":"1997","author":"karlsson","key":"ref14"},{"key":"ref15","first-page":"271","article-title":"Towards landscape analyses to inform the design of a hybrid local search for the multiobjective quadratic assignment problem","author":"knowles","year":"2002","journal-title":"Soft Computing Systems Design Management and Applications"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/3-540-36970-8_21","article-title":"Instance generators and test suites for the multiobjective quadratic assignment problem","author":"knowles","year":"2003","journal-title":"Conference on Evolutionary Multi-Criterion Optimization (EMO 2003)"},{"journal-title":"Proceedings of the Eighteenth Annual Conference on Neural Information Systems Processing (NIPS)","article-title":"Autonomous helicopter flight via reinforcement learning","year":"2004","author":"ng","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40988-2_2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2009.5178868"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511814068"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"ref6","first-page":"367","article-title":"A convergent online single time scale actor-critic algorithm","volume":"11","author":"castro","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45712-7_53"},{"key":"ref8","first-page":"17","article-title":"On the evolution of random graphs","volume":"5","author":"erd\u00f5s","year":"1960","journal-title":"Publications of the Mathematical Institute of the Hungarian Academy of Sciences"},{"journal-title":"In Proceedings of the International Conference on Computational Intelligence for Modelling Control and Automation (CIMCA)","article-title":"Multiple goal q-learning: Issues and functions","year":"2001","author":"crabbe","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2307\/2584329"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/358523.358553"},{"journal-title":"In Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems (NIPS)","article-title":"An application of reinforcement learning to acrobatic helicopter flight","year":"2006","author":"abbeel","key":"ref1"},{"journal-title":"Technical Report","article-title":"On the performance bounds of some policy search dynamic programming algorithms","year":"2013","author":"scherrer","key":"ref20"},{"key":"ref22","first-page":"2133","article-title":"RL-Glue: Language-independent software for reinforcement-learning experiments","volume":"10","author":"tanner","year":"2009","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref21"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1007\/978-3-540-89378-3_37","article-title":"On the limitations of scalarization for multi-objective reinforcement learning of pareto fronts","author":"vamplew","year":"2008","journal-title":"AI 2008 Advances in Artificial Intelligence"},{"key":"ref23","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"year":"0","key":"ref25"}],"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\/07010646.pdf?arnumber=7010646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T23:55:02Z","timestamp":1498175702000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010646\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010646","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}