{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T03:04:22Z","timestamp":1770519862531,"version":"3.49.0"},"reference-count":23,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,9,1]],"date-time":"2019-09-01T00:00:00Z","timestamp":1567296000000},"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":[[2019,9]]},"DOI":"10.1109\/etfa.2019.8869023","type":"proceedings-article","created":{"date-parts":[[2019,10,17]],"date-time":"2019-10-17T23:18:52Z","timestamp":1571354332000},"page":"459-466","source":"Crossref","is-referenced-by-count":9,"title":["Dynamic scheduling in modern processing systems using expert-guided distributed reinforcement learning"],"prefix":"10.1109","author":[{"given":"Shuhui","family":"Qu","sequence":"first","affiliation":[{"name":"Civil&Environmental Engineering, Stanford Unverisity, Palo Alto, CA, 94305, USA"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Sustainable Development and Global Competiveness, Stanford University, Palo Alto, CA, 94305, USA"}]},{"given":"Juergen","family":"Jasperneite","sequence":"additional","affiliation":[{"name":"Fraunhofer IOSB-INA, Lemgo, Germany"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Reinforcement Learning with Few Expert Demonstrations","author":"lakshminarayanan","year":"2016","journal-title":"NIPS workshop on Deep Learning for Action and Interaction"},{"key":"ref11","author":"lawrence","year":"1984","journal-title":"Resource constrained project scheduling An experimental investigation of heuristic scheduling techniques (Supplement)"},{"key":"ref12","article-title":"Reinforcement learning from multiple experts demonstration","author":"mao","year":"2018","journal-title":"Proceedings of the 29th International Joint Conference on Artificial Intelligence"},{"key":"ref13","author":"brendan mcmahan","year":"2009","journal-title":"Tighter bounds for multi-armed bandits with expert advice"},{"key":"ref14","first-page":"380","article-title":"Industrial scheduling","author":"muth","year":"1963","journal-title":"English Bibliography"},{"key":"ref15","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"nair","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)"},{"key":"ref16","author":"ontje","year":"2013","journal-title":"SimPy"},{"key":"ref17","author":"pinedo","year":"2016","journal-title":"Scheduling Theory Algorithms and Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA.2018.8502508"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA.2015.7301417"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1040.0170"},{"key":"ref3","author":"coates","year":"0","journal-title":"Reinforcement Learning with Multiple Demonstrations"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1160633.1160762"},{"key":"ref5","article-title":"Off-policy actor-critic","author":"degris","year":"2012"},{"key":"ref8","author":"hester","year":"2017","journal-title":"Deep Q-learning from Demonstrations"},{"key":"ref7","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"gupta","year":"2017","journal-title":"Proceedings of the Adaptive and Learning Agents workshop (at AAMAS 2017)"},{"key":"ref2","first-page":"3352","article-title":"Reinforcement learning from demonstration through shaping","author":"brys","year":"2015","journal-title":"International Conference on Artificial Intelligence"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/00207548208947745"},{"key":"ref9","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2008.2002557"},{"key":"ref22","first-page":"617","article-title":"Integrating reinforcement learning with human demonstrations of varying ability","author":"taylor","year":"2011","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref21","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/asjc.874"}],"event":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","location":"Zaragoza, Spain","start":{"date-parts":[[2019,9,10]]},"end":{"date-parts":[[2019,9,13]]}},"container-title":["2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8851311\/8868236\/08869023.pdf?arnumber=8869023","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:50:06Z","timestamp":1658155806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8869023\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/etfa.2019.8869023","relation":{},"subject":[],"published":{"date-parts":[[2019,9]]}}}