{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T06:42:11Z","timestamp":1782801731546,"version":"3.54.5"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"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":[[2021,12,5]]},"DOI":"10.1109\/ssci50451.2021.9660006","type":"proceedings-article","created":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T21:09:51Z","timestamp":1643058591000},"page":"1-8","source":"Crossref","is-referenced-by-count":6,"title":["Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Phillip","family":"Swazinna","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steffen","family":"Udluft","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Runkler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-27615-7_17"},{"key":"ref38","article-title":"Duckdq: Data quality assertions for machine learning pipelines","author":"doehmen","year":"0","journal-title":"Workshop on Challenges in Deploying and Monitoring ML Systems at the International Conference on Machine Learning (ICML)"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2166\/wst.2021.238"},{"key":"ref32","article-title":"Impact of wearable measurement properties and data quality on ADLs classification accuracy","author":"poli","year":"2020","journal-title":"IEEE Sensors Journal"},{"key":"ref31","article-title":"Federated noisy client learning","author":"li","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref30","first-page":"1","article-title":"Data quality considerations for big data and machine learning: Going beyond data cleaning and transformations","volume":"10","author":"gudivada","year":"2017","journal-title":"International Journal On Advances in Software"},{"key":"ref37","article-title":"Deequ-data quality validation for machine learning pipelines","author":"schelter","year":"0","journal-title":"Machine Learning Systems Workshop at the Conference on Neural Information Processing Systems (NeurIPS)"},{"key":"ref36","article-title":"Data validation for machine learning","author":"breck","year":"2019","journal-title":"MLSys"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401965"},{"key":"ref34","article-title":"Comparison between low-cost passive and active vision for obstacle depth","volume":"6","author":"chiarella","year":"2020","journal-title":"Revista de Ciência e Tecnologia (RCT)"},{"key":"ref10","first-page":"11 761","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","author":"kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref40","article-title":"Towards automated data quality management for machine learning","author":"rukat","year":"0","journal-title":"ML Ops Workshop at the Conference on ML and Systems (MLSys)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104366"},{"key":"ref12","article-title":"Behavior regularized offline reinforcement learning","author":"wu","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref13","article-title":"Conservative Q-learning for offline reinforcement learning","author":"kumar","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.14428\/esann\/2021.ES2021-83"},{"key":"ref15","article-title":"MOPO: Model-based offline policy optimization","author":"yu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Morel: Model-based offline reinforcement learning","author":"kidambi","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"COMBO: Conservative offline model-based policy optimization","author":"yu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref18","article-title":"Bayesian alignments of warped multi-output Gaussian processes","author":"kaiser","year":"2018","journal-title":"NeurIPS"},{"key":"ref19","article-title":"D4RL: Datasets for data-driven reinforcement learning","author":"fu","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref28","article-title":"NeoRL: A near real-world benchmark for offline reinforcement learning","author":"qin","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref4","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref27","article-title":"RL unplugged: Benchmarks for offline reinforcement learning","author":"gulcehre","year":"0","journal-title":"NeurIPS 2020"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"ArXiv Preprint"},{"key":"ref6","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541883"},{"key":"ref5","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.4018\/IJSIR.2016070102"},{"key":"ref7","article-title":"Learning and policy search in stochastic dynamical systems with Bayesian neural networks","author":"depeweg","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref2","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref9","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref1","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref20","article-title":"Hyperparameter selection for offline reinforcement learning","author":"paine","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280935"},{"key":"ref22","article-title":"Critic regularized regression","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref21","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"gretton","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2912574"},{"key":"ref24","article-title":"OPAL: Offline primitive discovery for accelerating offline reinforcement learning","author":"ajay","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref41","first-page":"61","article-title":"Automating data quality validation for dynamic data ingestion","author":"redyuk","year":"2021","journal-title":"EDBT"},{"key":"ref23","article-title":"Risk-averse offline reinforcement learning","author":"urp\u00ed","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/240455.240479"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1051"},{"key":"ref25","article-title":"Model-based offline planning","author":"argenson","year":"2020","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Orlando, FL, USA","start":{"date-parts":[[2021,12,5]]},"end":{"date-parts":[[2021,12,7]]}},"container-title":["2021 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9659537\/9659538\/09660006.pdf?arnumber=9660006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:56:45Z","timestamp":1652201805000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9660006\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,5]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ssci50451.2021.9660006","relation":{},"subject":[],"published":{"date-parts":[[2021,12,5]]}}}