{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T07:07:55Z","timestamp":1774940875553,"version":"3.50.1"},"reference-count":33,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,7]]},"DOI":"10.1109\/ijcnn.2014.6889732","type":"proceedings-article","created":{"date-parts":[[2014,9,10]],"date-time":"2014-09-10T10:30:33Z","timestamp":1410345033000},"page":"2315-2322","source":"Crossref","is-referenced-by-count":35,"title":["Multi-objectivization of reinforcement learning problems by reward shaping"],"prefix":"10.1109","author":[{"given":"Tim","family":"Brys","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Harutyunyan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Vrancx","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew E.","family":"Taylor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Kudenko","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ann","family":"Nowe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1145\/1569901.1569984"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44719-9_19"},{"key":"18","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/978-3-540-87700-4_4","article-title":"Multiobjectivization by decomposition of scalar cost functions","author":"handl","year":"2008","journal-title":"Parallel Problem Solving from Nature-PPSN X"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2188528"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1007\/BF01197559"},{"key":"13","article-title":"Multi-criteria reinforcement learning","author":"g\ufffdbor","year":"1998","journal-title":"International Conference on Machine Learning"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6615007"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"},{"key":"12","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1613\/jair.3987","article-title":"A survey of multi-objective sequential decision-making","volume":"48","author":"roijers","year":"2013","journal-title":"Journal of Artificial Intelligence Research"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1145\/1276958.1277114"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1023\/B:JMMA.0000049378.57591.c6"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03625-5_5"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39742-4_28"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2005.1554895"},{"key":"25","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1109\/CEC.2007.4424568","article-title":"Trading on infeasibility by exploiting constraints criticality through multi-objectivization: A system design perspective","author":"saxena","year":"2007","journal-title":"Evolutionary Computation 2007 CEC 2007 IEEE Congress on"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(90)90005-D"},{"key":"27","first-page":"118","article-title":"Pareto optimality, GA-easiness and deception","author":"louis","year":"1993","journal-title":"ICGA"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2012.32"},{"key":"29","volume":"414","author":"puterman","year":"2009","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"3","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume":"99","author":"ng","year":"1999","journal-title":"ICML"},{"key":"2","first-page":"463","article-title":"Learning to drive a bicycle using reinforcement learning and shaping","author":"randlov","year":"1998","journal-title":"Proceedings of the Fifteenth International Conference on Machine Learning"},{"key":"10","article-title":"Brain function and adaptive systems: A heterostatic theory","author":"klopf","year":"1972","journal-title":"US Air Force Cambridge Research Laboratories"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50030-1"},{"key":"30","article-title":"Adaptive objective selection for correlated objectives in multi-objective reinforcement learning","author":"brys","year":"2014","journal-title":"The 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"7","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"6","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"32","article-title":"An ensemble of linearly combined reinforcement-learning agents","author":"marivate","year":"2013","journal-title":"Workshops at the Twenty-seventh AAAI Conference on Artificial Intelligence"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2013.6633622"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920231"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1142\/S0219525911002998"},{"key":"9","author":"albus","year":"1981","journal-title":"Brains Behavior and Robotics"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"}],"event":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","location":"Beijing, China","start":{"date-parts":[[2014,7,6]]},"end":{"date-parts":[[2014,7,11]]}},"container-title":["2014 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6880678\/6889358\/06889732.pdf?arnumber=6889732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T11:17:29Z","timestamp":1602674249000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6889732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2014.6889732","relation":{},"subject":[],"published":{"date-parts":[[2014,7]]}}}