{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T21:07:05Z","timestamp":1762376825206,"version":"3.28.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,30]],"date-time":"2020-08-30T00:00:00Z","timestamp":1598745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,30]],"date-time":"2020-08-30T00:00:00Z","timestamp":1598745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,30]],"date-time":"2020-08-30T00:00:00Z","timestamp":1598745600000},"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":[[2020,8,30]]},"DOI":"10.1109\/ccece47787.2020.9255795","type":"proceedings-article","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T00:26:07Z","timestamp":1605831967000},"page":"1-8","source":"Crossref","is-referenced-by-count":11,"title":["Multi-Agent Reinforcement Learning for the Energy Optimization of Cyber-Physical Production Systems"],"prefix":"10.1109","author":[{"given":"Jupiter","family":"Bakakeu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dominik","family":"Kisskalt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joerg","family":"Franke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shirin","family":"Baer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hans-Henning","family":"Klos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joern","family":"Peschke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"abs 1605 6676","author":"foerster","year":"2016","journal-title":"CoRR"},{"key":"ref38","article-title":"Emergence of grounded compositional language in multi-agent populations","volume":"abs 1703 4908","author":"mordatch","year":"2017","journal-title":"CoRR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"journal-title":"Multiagent Cooperation and Competition with Deep Reinforcement Learning","year":"2015","author":"tampuu","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref37","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref36","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"0","journal-title":"AAAI"},{"key":"ref35","volume":"abs 1706 2275","author":"lowe","year":"2017","journal-title":"Multi-agent actor-critic for mixed cooperative-competitive environments"},{"journal-title":"Stabilising experience replay for deep multi-agent reinforcement learning","year":"2017","author":"foerster","key":"ref34"},{"key":"ref10","first-page":"1","article-title":"An integrated optimization model for generation and batch production load scheduling in energy intensive enterprise","author":"wang","year":"0","journal-title":"2012 IEEE Power and Energy Society General Meeting"},{"key":"ref40","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"abs 1803 11485","author":"rashid","year":"2018","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2008.09.011"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2012.2216876"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirp.2012.05.002"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-19692-8_51"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cirp.2012.03.084"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2011.08.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0954-1810(97)00004-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2013.2256856"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/PSCC.2014.7038106"},{"key":"ref28","article-title":"Multiagent reinforcement learning: Theoretical framework and an algorithm","author":"hu","year":"0","journal-title":"ICML"},{"journal-title":"Solving Rubik’s Cube with a Robot Hand","year":"2019","author":"akkaya","key":"ref4"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref3","article-title":"Playing atari with deep reinforcement learning","volume":"abs 1312 5602","author":"mnih","year":"2013","journal-title":"CoRR"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"journal-title":"Deep recurrent q-learning for partially observable mdps","year":"2015","author":"hausknecht","key":"ref5"},{"journal-title":"EMERGENT COMPLEXITY VIA MULTI-AGENT COMPETITION","year":"2017","author":"bansal","key":"ref8"},{"journal-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","year":"2017","author":"lowe","key":"ref7"},{"journal-title":"Reinforcement Learning An Introduction (Adaptive Computation and Machine Learning Series)","year":"2018","author":"sutton","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2015.08.018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2468577"},{"journal-title":"Multi-agent-rl-energy-management","year":"2020","author":"bakakeu","key":"ref46"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2640184"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref45"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2017.12.019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISGTEurope.2017.8260152"},{"key":"ref42","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","author":"he","year":"0","journal-title":"Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2017.06.007"},{"key":"ref41","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proc of International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2014.2347043"},{"key":"ref44","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","author":"jiang","year":"2018","journal-title":"Proceedings of the 32Nd International Conference on Neural Information Processing Systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.03.072"},{"key":"ref43","volume":"abs 1712 4603","author":"choi","year":"2017","journal-title":"Multi-focus attention network for efficient deep reinforcement learning"},{"journal-title":"Multi-agent deep reinforcement learning for zero energy communities","year":"2018","author":"prasad","key":"ref25"}],"event":{"name":"2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","start":{"date-parts":[[2020,8,30]]},"location":"London, ON, Canada","end":{"date-parts":[[2020,9,2]]}},"container-title":["2020 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9255668\/9255669\/09255795.pdf?arnumber=9255795","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T17:49:04Z","timestamp":1656438544000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9255795\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ccece47787.2020.9255795","relation":{},"subject":[],"published":{"date-parts":[[2020,8,30]]}}}