{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T02:50:19Z","timestamp":1767840619065,"version":"3.49.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T00:00:00Z","timestamp":1664236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T00:00:00Z","timestamp":1664236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation (NSF)","doi-asserted-by":"publisher","award":["2210012"],"award-info":[{"award-number":["2210012"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,27]]},"DOI":"10.1109\/allerton49937.2022.9929321","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T21:34:30Z","timestamp":1667597670000},"page":"1-8","source":"Crossref","is-referenced-by-count":10,"title":["Reinforcement Learning using Physics Inspired Graph Convolutional Neural Networks"],"prefix":"10.1109","author":[{"given":"Tong","family":"Wu","sequence":"first","affiliation":[{"name":"Cornell Tech, Cornell University,Department of Electrical and Computer Engineering,New York City,NY,USA,10044"}]},{"given":"Anna","family":"Scaglione","sequence":"additional","affiliation":[{"name":"Cornell Tech, Cornell University,Department of Electrical and Computer Engineering,New York City,NY,USA,10044"}]},{"given":"Daniel","family":"Arnold","sequence":"additional","affiliation":[{"name":"Lawrence Berkeley National Laboratory"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep reinforcement learning and the deadly triad","author":"van hasselt","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref11","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"29","author":"defferrard","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2004.831259"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2019.2948132"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2951769"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2019.2941134"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2990179"},{"key":"ref17","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.3000652"},{"key":"ref19","article-title":"Learning sequential distribution system restoration via graph-reinforcement learning","author":"zhao","year":"2021","journal-title":"IEEE Transactions on Power Systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3010130"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3052998"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SmartGridComm47815.2020.9302997"},{"key":"ref5","article-title":"Deep reinforcement learning enabled physical-model-free two-timescale volt-age control method for active distribution systems","author":"cao","year":"2021","journal-title":"IEEE Transactions on Smart Grid"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref7","article-title":"Reinforcement learning for decision-making and control in power systems: Tutorial, review, and vision","author":"chen","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3058996"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3041620"},{"key":"ref9","first-page":"18","article-title":"Emphatic algorithms for deep reinforcement learning","volume":"139","author":"jiang","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"ref20","article-title":"A graph policy network approach for volt-var control in power distribution systems","author":"lee","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3075145"},{"key":"ref21","author":"wu","year":"2022","journal-title":"Graph convolutional neural networks for physics-aware grid learning algorithms"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482815"},{"key":"ref23","article-title":"Prox-imal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"ArXiv Preprint"}],"event":{"name":"2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","location":"Monticello, IL, USA","start":{"date-parts":[[2022,9,27]]},"end":{"date-parts":[[2022,9,30]]}},"container-title":["2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9929313\/9929314\/09929321.pdf?arnumber=9929321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T20:26:00Z","timestamp":1669667160000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9929321\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,27]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/allerton49937.2022.9929321","relation":{},"subject":[],"published":{"date-parts":[[2022,9,27]]}}}