{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T07:16:28Z","timestamp":1768547788477,"version":"3.49.0"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197456","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"7484-7490","source":"Crossref","is-referenced-by-count":7,"title":["Predicting optimal value functions by interpolating reward functions in scalarized multi-objective reinforcement learning"],"prefix":"10.1109","author":[{"given":"Arpan","family":"Kusari","sequence":"first","affiliation":[]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"514","article-title":"Gaussian processes for regression","author":"williams","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref12","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref13","first-page":"63","article-title":"Gaussian processes in machine learning","author":"rasmussen","year":"2003","journal-title":"Machine Learning Summer School"},{"key":"ref14","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref15","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"ref16","first-page":"19","article-title":"Nonlinear inverse reinforcement learning with gaussian processes","author":"levine","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref19","first-page":"1","article-title":"GPflow: A Gaussian process library using TensorFlow","volume":"18","author":"matthews","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"ref4","volume":"164","author":"hwang","year":"2012","journal-title":"Multiple Objective Decision Making Methods and Application A State of Art Survey"},{"key":"ref3","first-page":"3483","article-title":"Multi-objective reinforcement learning using sets of pareto dominating policies","volume":"15","author":"van moffaert","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"ref6","article-title":"Convergent reinforcement learning with value function interpolation","volume":"1121","author":"szepesv\u00e1ri","year":"2001","journal-title":"Technical Report TR-2001-02"},{"key":"ref5","first-page":"1005","article-title":"Multidimensional triangulation and interpolation for reinforcement learning","author":"davies","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390162"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.090"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1076\/vesd.35.1.19.5614"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"ref9","article-title":"Multi-objective monte-carlo tree search","author":"wang","year":"2012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF01197559"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197456.pdf?arnumber=9197456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:23:27Z","timestamp":1656375807000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197456\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197456","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}