{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T11:53:44Z","timestamp":1781610824340,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"The Danish Industry Foundation","award":["2021-0164"],"award-info":[{"award-number":["2021-0164"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3744255.3811744","type":"proceedings-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T10:13:49Z","timestamp":1781604829000},"page":"303-320","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FOgym: A Bottom-Up Home Energy Management Framework Based on FlexOffers and Multi-Agent Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2289-6413","authenticated-orcid":false,"given":"Jiachen","family":"Xu","sequence":"first","affiliation":[{"name":"Aalborg University, Aalborg, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1615-777X","authenticated-orcid":false,"given":"Torben Bach","family":"Pedersen","sequence":"additional","affiliation":[{"name":"Aalborg University, Aalborg, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6463-9195","authenticated-orcid":false,"given":"Zhongming","family":"Yao","sequence":"additional","affiliation":[{"name":"Aalborg University, Aalborg, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5424-6442","authenticated-orcid":false,"given":"Tianyi","family":"Li","sequence":"additional","affiliation":[{"name":"Aalborg University, Aalborg, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3043-3777","authenticated-orcid":false,"given":"Yushuai","family":"Li","sequence":"additional","affiliation":[{"name":"Aalborg University, Aalborg, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Johannes Ackermann Volker Gabler Takayuki Osa and Masashi Sugiyama. 2019. Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics. Deep RL Workshop at Advances in Neural Information Processing Systems (2019)."},{"key":"e_1_3_3_2_3_2","unstructured":"Tianyu Chen and Wencong Su. 2023. Decentralized Coordination of Distributed Energy Resources through Local Energy Markets and Deep Reinforcement Learning. Applied Energy 349 (2023) 121625."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Che-Wei Chou Wei-Cheng Chiu and Yu-Teng Hsu. 2025. Multiagent Reinforcement Learning-Based Dispatching Model for Overhead Hoist Transfer in Automated Material Handling System. Computers & Industrial Engineering 204 (2025) 111109.","DOI":"10.1016\/j.cie.2025.111109"},{"key":"e_1_3_3_2_5_2","unstructured":"Andreas Doms Zoran Marinzek and Torben\u00a0Bach Pedersen. 2013. Mirabel-Efficiently Managing More Renewable Energy Using Explicit Demand and Supply Flexibilities. World Smart Grid Forum (2013)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Benjamin Ellis Jonathan Cook Skander Moalla Mikayel Samvelyan Mingfei Sun Anuj Mahajan Jakob Foerster and Shimon Whiteson. 2023. SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning. 36 (2023) 37567\u201337593.","DOI":"10.52202\/075280-1634"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/323"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Jian Gao Yufeng Li Yimin Chen Yaozhen He and Jingwei Guo. 2024. An Improved SAC-Based Deep Reinforcement Learning Framework for Collaborative Pushing and Grasping in Underwater Environments. IEEE Transactions on Instrumentation and Measurement 73 (2024) 1\u201314.","DOI":"10.1109\/TIM.2024.3379048"},{"key":"e_1_3_3_2_9_2","first-page":"2961","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","volume":"97","author":"Iqbal Shariq","year":"2019","unstructured":"Shariq Iqbal and Fei Sha. 2019. Actor-Attention-Critic for Multi-Agent Reinforcement Learning. In Proceedings of the 36th International Conference on Machine Learning (ICML), Vol.\u00a097. 2961\u20132970."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Hamish Ivison Yizhong Wang Jiacheng Liu Zeqiu Wu Valentina Pyatkin Nathan Lambert Noah\u00a0A. Smith Yejin Choi and Hanna Hajishirzi. 2024. Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback. 37 (2024) 36602\u201336633.","DOI":"10.52202\/079017-1154"},{"key":"e_1_3_3_2_11_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Jiang Jiechuan","year":"2020","unstructured":"Jiechuan Jiang, Chen Dun, Tiejun Huang, and Zongqing Lu. 2020. Graph Convolutional Reinforcement Learning. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21169"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Tianxu Li Kun Zhu Nguyen\u00a0Cong Luong Dusit Niyato Qihui Wu Yang Zhang and Bing Chen. 2022. Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey. IEEE Communications Surveys & Tutorials 24 2 (2022) 1240\u20131279.","DOI":"10.1109\/COMST.2022.3160697"},{"key":"e_1_3_3_2_14_2","unstructured":"Wenhao Li Bo Jin Xiangfeng Wang Junchi Yan and Hongyuan Zha. 2023. F2a2: Flexible Fully-Decentralized Approximate Actor-Critic for Cooperative Multi-Agent Reinforcement Learning. Journal of Machine Learning Research 24 178 (2023) 1\u201375."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Yuanzheng Li Chaofan Yu Mohammad Shahidehpour Tao Yang Zhigang Zeng and Tianyou Chai. 2023. Deep Reinforcement Learning for Smart Grid Operations: Algorithms Applications and Prospects. Proc. IEEE 111 9 (2023) 1055\u20131096.","DOI":"10.1109\/JPROC.2023.3303358"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/SmartGridComm51999.2021.9631999"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575813.3597347"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3538637.3538876"},{"key":"e_1_3_3_2_19_2","unstructured":"Ryan Lowe Yi\u00a0I Wu Aviv Tamar Jean Harb OpenAI Pieter\u00a0Abbeel and Igor Mordatch. 2017. Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Jiaming Luo Shibin Gao Xiaoguang Wei Zhongbei Tian and Xin Wang. 2023. Parallel-Reinforcement-Learning-Based Online Energy Management Strategy for Energy Storage Traction Substations in Electrified Railroad. IEEE Transactions on Transportation Electrification 10 1 (2023) 2112\u20132123.","DOI":"10.1109\/TTE.2023.3288639"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Luca Massidda and Marino Marrocu. 2025. Hybrid Forecasting of Demand Flexibility: A Top-Down Approach for Thermostatically Controlled Loads. Energy and AI 20 (2025) 100487.","DOI":"10.1016\/j.egyai.2025.100487"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Stephanie Milani Nicholay Topin Manuela Veloso and Fei Fang. 2024. Explainable Reinforcement Learning: A Survey and Comparative Review. Comput. Surveys 56 7 (2024).","DOI":"10.1145\/3616864"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3077839.3077850"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3538637.3538865"},{"key":"e_1_3_3_2_25_2","volume-title":"Workshop on Tackling Climate Change with Machine Learning at International Conference on Learning Representations","author":"Nunez-Jimenez Alejandro","year":"2023","unstructured":"Alejandro Nunez-Jimenez, Enrique\u00a0Munoz De\u00a0Cote, and Nidhi Suri. 2023. MAHTM: A Multi-Agent Framework for Hierarchical Transactive Microgrids. In Workshop on Tackling Climate Change with Machine Learning at International Conference on Learning Representations."},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/SmartGridComm.2018.8587605"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34494"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"El\u00e9a Prat Irena Dukovska Rahul Nellikkath Malte Thoma Lars Herre and Spyros Chatzivasileiadis. 2024. Network-Aware Flexibility Requests for Distribution-Level Flexibility Markets. IEEE Transactions on Power Systems 39 2 (2024) 2641\u20132652.","DOI":"10.1109\/TPWRS.2023.3280366"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Paolo Scarabaggio Raffaele Carli and Mariagrazia Dotoli. 2022. Noncooperative Equilibrium-Seeking in Distributed Energy Systems Under AC Power Flow Nonlinear Constraints. IEEE Transactions on Control of Network Systems 9 4 (2022) 1731\u20131742.","DOI":"10.1109\/TCNS.2022.3181527"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3679240.3734683"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3632775.3661946"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13290-7_2"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3208903.3208936"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6220"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Hao Xiao Xiaowei Pu Wei Pei Li Ma and Tengfei Ma. 2023. A Novel Energy Management Method for Networked Multi-Energy Microgrids Based on Improved DQN. IEEE Transactions on Smart Grid 14 6 (2023) 4912\u20134926.","DOI":"10.1109\/TSG.2023.3261979"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Haotian Xu Junyu Xuan Guangquan Zhang and Jie Lu. 2025. Twin Trust Region Policy Optimization. IEEE Transactions on Systems Man and Cybernetics: Systems 55 8 (2025) 5422\u20135436.","DOI":"10.1109\/TSMC.2025.3573513"},{"key":"e_1_3_3_2_37_2","series-title":"Proceedings of Machine Learning Research","first-page":"5567","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","volume":"80","author":"Yang Yaodong","year":"2018","unstructured":"Yaodong Yang, Rui Luo, Minne Li, Ming Zhou, Weinan Zhang, and Jun Wang. 2018. Mean Field Multi-Agent Reinforcement Learning. In Proceedings of the 35th International Conference on Machine Learning (ICML)(Proceedings of Machine Learning Research, Vol.\u00a080). 5567\u20135576."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Chao Yu Akash Velu Eugene Vinitsky Jiaxuan Gao Yu Wang Alexandre Bayen and Yi Wu. 2022. The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games. Advances in Neural Information Processing Systems 35 (2022) 24611\u201324624.","DOI":"10.52202\/068431-1787"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Bin Zhang Weihao Hu Amer M.Y.M. Ghias Xiao Xu and Zhe Chen. 2023. Multi-Agent Deep Reinforcement Learning Based Distributed Control Architecture for Interconnected Multi-Energy Microgrid Energy Management and Optimization. Energy Conversion and Management 277 (2023) 116647.","DOI":"10.1016\/j.enconman.2022.116647"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Hao Zhang Boli Chen Nuo Lei Bingbing Li Rulong Li and Zhi Wang. 2023. Integrated Thermal and Energy Management of Connected Hybrid Electric Vehicles Using Deep Reinforcement Learning. IEEE Transactions on Transportation Electrification 10 2 (2023) 4594\u20134603.","DOI":"10.1109\/TTE.2023.3309396"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Miaomiao Zhang Wei Tong Guangyu Zhu Xin Xu and Edmond\u00a0Q. Wu. 2024. SQIX: QMIX Algorithm Activated by General Softmax Operator for Cooperative Multiagent Reinforcement Learning. IEEE Transactions on Systems Man and Cybernetics: Systems 54 11 (2024) 6550\u20136560.","DOI":"10.1109\/TSMC.2024.3370186"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Xiaoyu Zhang Yushuai Li Tianyi Li Yonghao Gui Qiuye Sun and David\u00a0Wenzhong Gao. 2024. Digital Twin Empowered PV Power Prediction. Journal of Modern Power Systems and Clean Energy 12 5 (2024) 1472\u20131483.","DOI":"10.35833\/MPCE.2023.000351"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Yihuan Zhou Zhiping Xia Xingbo Liu Zhonghua Deng Xiaowei Fu Jakub Kupecki Bing Jin and Xi Li. 2023. Online Energy Management Optimization of Hybrid Energy Storage Microgrid with Reversible Solid Oxide Cell: A Model-Based Study. Journal of Cleaner Production 423 (2023) 138663.","DOI":"10.1016\/j.jclepro.2023.138663"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"crossref","unstructured":"Laurynas \u0160ik\u0161nys Emmanouil Valsomatzis Katja Hose and Torben\u00a0Bach Pedersen. 2015. Aggregating and Disaggregating Flexibility Objects. IEEE Transactions on Knowledge and Data Engineering 27 11 (2015) 2893\u20132906.","DOI":"10.1109\/TKDE.2015.2445755"}],"event":{"name":"E-Energy '26: The 17th ACM International Conference on Future and Sustainable Energy Systems","location":"Banff , Alberta , Canada","acronym":"E-Energy '26","sponsor":["SIGENERGY ACM Special Interest Group on Energy Systems and Informatics"]},"container-title":["Proceedings of the 17th ACM International Conference on Future and Sustainable Energy Systems"],"original-title":[],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T11:16:13Z","timestamp":1781608573000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3744255.3811744"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":43,"alternative-id":["10.1145\/3744255.3811744","10.1145\/3744255"],"URL":"https:\/\/doi.org\/10.1145\/3744255.3811744","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}