{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T22:10:08Z","timestamp":1755900608990,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":13,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,15]],"date-time":"2023-11-15T00:00:00Z","timestamp":1700006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,15]]},"DOI":"10.1145\/3600100.3626276","type":"proceedings-article","created":{"date-parts":[[2023,11,3]],"date-time":"2023-11-03T12:17:16Z","timestamp":1699013836000},"page":"314-315","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Heterogeneous Multi-Agent Reinforcement Learning for Grid-Interactive Communities"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4114-0371","authenticated-orcid":false,"given":"Allen","family":"Wu","sequence":"first","affiliation":[{"name":"The University of Texas at Austin, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1239-5540","authenticated-orcid":false,"given":"Kingsley","family":"Nweye","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6014-3228","authenticated-orcid":false,"given":"Zoltan","family":"Nagy","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, United States of America"}]}],"member":"320","published-online":{"date-parts":[[2023,11,15]]},"reference":[{"volume-title":"NeurIPS 2022 - The CityLearn Challenge","year":"2022","key":"e_1_3_2_1_1_1","unstructured":"2022. NeurIPS 2022 - The CityLearn Challenge 2022. https:\/\/www.aicrowd.com\/challenges\/neurips-2022-citylearn-challenge"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3427773.3427870"},{"key":"e_1_3_2_1_3_1","unstructured":"Siyi Hu Yifan Zhong Minquan Gao Weixun Wang Hao Dong Xiaodan Liang Zhihui Li Xiaojun Chang and Yaodong Yang. 2023. MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library. arxiv:2210.13708\u00a0[cs.LG]"},{"key":"e_1_3_2_1_4_1","volume-title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning. CoRR abs\/2109.11251","author":"Kuba Jakub\u00a0Grudzien","year":"2021","unstructured":"Jakub\u00a0Grudzien Kuba, Ruiqing Chen, Muning Wen, Ying Wen, Fanglei Sun, Jun Wang, and Yaodong Yang. 2021. Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning. CoRR abs\/2109.11251 (2021). arXiv:2109.11251https:\/\/arxiv.org\/abs\/2109.11251"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3486611.3492226"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2023.121323"},{"key":"e_1_3_2_1_7_1","volume-title":"Trust Region Policy Optimization. CoRR abs\/1502.05477","author":"Schulman John","year":"2015","unstructured":"John Schulman, Sergey Levine, Philipp Moritz, Michael\u00a0I. Jordan, and Pieter Abbeel. 2015. Trust Region Policy Optimization. CoRR abs\/1502.05477 (2015). arXiv:1502.05477http:\/\/arxiv.org\/abs\/1502.05477"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Shai Shalev-Shwartz Shaked Shammah and Amnon Shashua. 2016. Safe Multi-Agent Reinforcement Learning for Autonomous Driving. https:\/\/doi.org\/10.48550\/arXiv.1610.03295 arXiv:1610.03295 [cs stat].","DOI":"10.48550\/arXiv.1610.03295"},{"key":"e_1_3_2_1_9_1","volume-title":"CityLearn: Standardizing Research in Multi-Agent Reinforcement Learning for Demand Response and Urban Energy Management. arXiv (Dec","author":"Vazquez-Canteli R","year":"2020","unstructured":"Jose\u00a0R Vazquez-Canteli, Sourav Dey, Gregor Henze, and Zoltan Nagy. 2020. CityLearn: Standardizing Research in Multi-Agent Reinforcement Learning for Demand Response and Urban Energy Management. arXiv (Dec. 2020). http:\/\/arxiv.org\/abs\/2012.10504"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3360322.3360998"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3408308.3431122"},{"key":"e_1_3_2_1_13_1","volume-title":"Multi-Agent Games. CoRR abs\/2103.01955","author":"Yu Chao","year":"2021","unstructured":"Chao Yu, Akash Velu, Eugene Vinitsky, Yu Wang, Alexandre\u00a0M. Bayen, and Yi Wu. 2021. The Surprising Effectiveness of MAPPO in Cooperative, Multi-Agent Games. CoRR abs\/2103.01955 (2021). arXiv:2103.01955https:\/\/arxiv.org\/abs\/2103.01955"}],"event":{"name":"BuildSys '23: The 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","acronym":"BuildSys '23","location":"Istanbul Turkey"},"container-title":["Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3600100.3626276","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3600100.3626276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T21:30:29Z","timestamp":1755898229000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3600100.3626276"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,15]]},"references-count":13,"alternative-id":["10.1145\/3600100.3626276","10.1145\/3600100"],"URL":"https:\/\/doi.org\/10.1145\/3600100.3626276","relation":{},"subject":[],"published":{"date-parts":[[2023,11,15]]},"assertion":[{"value":"2023-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}