{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T08:27:40Z","timestamp":1765268860067},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T00:00:00Z","timestamp":1662422400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,6]],"date-time":"2022-09-06T00:00:00Z","timestamp":1662422400000},"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":[[2022,9,6]]},"DOI":"10.23919\/sice56594.2022.9905798","type":"proceedings-article","created":{"date-parts":[[2022,10,6]],"date-time":"2022-10-06T19:43:18Z","timestamp":1665085398000},"page":"468-474","source":"Crossref","is-referenced-by-count":4,"title":["Local Control is All You Need: Decentralizing and Coordinating Reinforcement Learning for Large-Scale Process Control"],"prefix":"10.23919","author":[{"given":"Nicolas","family":"Bougie","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,NEC-AIST AI Cooperative Research Laboratory,Tokyo,Japan"}]},{"given":"Takashi","family":"Onishi","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,NEC-AIST AI Cooperative Research Laboratory,Tokyo,Japan"}]},{"given":"Yoshimasa","family":"Tsuruoka","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology,NEC-AIST AI Cooperative Research Laboratory,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3040","article-title":"Social influence as intrinsic motivation for multiagent deep reinforcement learning","author":"jaques","year":"2019","journal-title":"Conference on Machine Learning"},{"key":"ref11","first-page":"4455","article-title":"One policy to control them all: Shared modular policies for agent-agnostic control","author":"huang","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2016.07.397"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1004829"},{"key":"ref14","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proceedings of the International Conference on Machine Learning"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref15"},{"article-title":"Adam: A method for stochastic optimization","year":"2014","author":"kingma","key":"ref16"},{"article-title":"Soft actor-critic algorithms and applications","year":"2018","author":"haarnoja","key":"ref17"},{"key":"ref18","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2021.104878"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COASE.2018.8560593"},{"key":"ref6","article-title":"Non-steady state control under disturbances: Navigation plant operation via simulation-based reinforcement learning","author":"kubosawa","year":"21","journal-title":"Annual Conference of the Society of Instrument and Control Engineers of Japan"},{"key":"ref5","article-title":"Improving the gross profit of a vinyl acetate monomer plant by deep reinforcement learning","author":"mori","year":"2020","journal-title":"Annual Conference of the Society of Instrument and Control Engineers of Japan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11798"},{"key":"ref7","article-title":"Synthesizing chemical plant operation procedures using knowledge, dynamic simulation and deep reinforcement learning","author":"kubosawa","year":"2019","journal-title":"ArXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2020.104331"},{"article-title":"Deep reinforcement learning for process control: A primer for beginners","year":"2020","author":"spielberg","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2022.107658"}],"event":{"name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","start":{"date-parts":[[2022,9,6]]},"location":"Kumamoto, Japan","end":{"date-parts":[[2022,9,9]]}},"container-title":["2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9905734\/9905735\/09905798.pdf?arnumber=9905798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:52Z","timestamp":1670284852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9905798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,6]]},"references-count":18,"URL":"https:\/\/doi.org\/10.23919\/sice56594.2022.9905798","relation":{},"subject":[],"published":{"date-parts":[[2022,9,6]]}}}