{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T02:45:58Z","timestamp":1769741158100,"version":"3.49.0"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T00:00:00Z","timestamp":1734134400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T00:00:00Z","timestamp":1734134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the National Natural Science Foundation of China: \"Thermal Landscape construction and Energy-Saving Design Methods for Building Public Spaces\"","award":["No. 52078341"],"award-info":[{"award-number":["No. 52078341"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s00607-024-01378-8","type":"journal-article","created":{"date-parts":[[2024,12,14]],"date-time":"2024-12-14T12:28:24Z","timestamp":1734179304000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Indoor energy-saving strategy optimization based on deep reinforcement learning and DDPG algorithm"],"prefix":"10.1007","volume":"107","author":[{"given":"Yan","family":"Wan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujia","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dexuan","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,14]]},"reference":[{"key":"1378_CR1","doi-asserted-by":"crossref","unstructured":"Chen B, Cai Z, Berg\u00e9s M (2019) Gnu-RL. A precocial reinforcement learning solution for building hvac control using a differentiable MPC policy. In: Proceedings of the 6th ACM international conference on systems for energy efficient buildings, cities, and transportation, pp 316\u2013325","DOI":"10.1145\/3360322.3360849"},{"issue":"3","key":"1378_CR2","first-page":"5","volume":"2","author":"T Yang","year":"2021","unstructured":"Yang T, Zhao L, Li W, Zomaya AY (2021) Dynamic energy dispatch strategy for integrated energy system based on improved deep reinforcement learning. Energy 2(3):5","journal-title":"Energy"},{"issue":"1","key":"1378_CR3","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1109\/TSG.2020.3011739","volume":"12","author":"L Yu","year":"2020","unstructured":"Yu L, Sun Y, Xu Z et al (2020) Multi-agent deep reinforcement learning for HVAC control in commercial buildings. IEEE Trans Smart Grid 12(1):407\u2013419","journal-title":"IEEE Trans Smart Grid"},{"key":"1378_CR4","doi-asserted-by":"publisher","first-page":"2445","DOI":"10.3390\/en12122445","volume":"12","author":"P Liu","year":"2019","unstructured":"Liu P, Zheng P, Chen Z (2019) Deep learning with stacked denoising auto-encoder for short-term electric load forecasting. Energies 12:2445","journal-title":"Energies"},{"issue":"1","key":"1378_CR5","doi-asserted-by":"publisher","first-page":"51","DOI":"10.3390\/biomimetics9010051","volume":"9","author":"M Park","year":"2024","unstructured":"Park M, Park C, Kwon NK (2024) Autonomous driving of mobile robots in dynamic environments based on deep deterministic policy gradient: reward shaping and hindsight experience replay. Biomimetics 9(1):51","journal-title":"Biomimetics"},{"issue":"3","key":"1378_CR6","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/s10723-024-09774-2","volume":"22","author":"Z Zhou","year":"2024","unstructured":"Zhou Z, Wang Q, Li J, Li Z (2024) Resource allocation using deep deterministic policy gradient-based federated learning for multi-access edge computing. J Grid Comput 22(3):59","journal-title":"J Grid Comput"},{"key":"1378_CR7","doi-asserted-by":"publisher","first-page":"8472","DOI":"10.1109\/JIOT.2020.2992117","volume":"7","author":"G Gao","year":"2019","unstructured":"Gao G, Li J, Wen Y (2019) Energy-efficient thermal comfort control in smart buildings via deep reinforcement learning. IEEE Internet Things J 7:8472\u20138484","journal-title":"IEEE Internet Things J"},{"key":"1378_CR8","doi-asserted-by":"crossref","unstructured":"Morinibu T, Noda T, Shota T (2019) Application of deep reinforcement learning in residential preconditioning for radiation temperature. In: Proceedings of 2019 8th international congress on advanced applied informatics, pp 561\u2013566.","DOI":"10.1109\/IIAI-AAI.2019.00120"},{"issue":"10","key":"1378_CR9","doi-asserted-by":"publisher","first-page":"9919","DOI":"10.1109\/JIOT.2020.2989696","volume":"7","author":"X Deng","year":"2020","unstructured":"Deng X, Jiang Y, Yang LT et al (2020) Learning automata based confident information coverage barriers for smart ocean internet of things. IEEE Internet Things J 7(10):9919\u20139929","journal-title":"IEEE Internet Things J"},{"key":"1378_CR10","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.1016\/j.apenergy.2018.11.002","volume":"235","author":"JR Vazquez-Canteli","year":"2019","unstructured":"Vazquez-Canteli JR, Nagy Z (2019) Reinforcement learning for demand response: a review of algorithms and modeling techniques. Appl Energy 235:1072\u20131089","journal-title":"Appl Energy"},{"key":"1378_CR11","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.buildenv.2019.03.038","volume":"155","author":"W Valladares","year":"2019","unstructured":"Valladares W, Galindo M, Guti\u00e9rrez J et al (2019) Energy optimization associated with thermal comfort and indoor air control via a deep reinforcement learning algorithm. Build Environ 155:105\u2013117","journal-title":"Build Environ"},{"issue":"1","key":"1378_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-021-25874-z","volume":"12","author":"A Gupta","year":"2021","unstructured":"Gupta A, Savarese S, Ganguli S et al (2021) Embodied intelligence via learning and evolution. Nat Commun 12(1):1\u201312","journal-title":"Nat Commun"},{"key":"1378_CR13","first-page":"1","volume":"34","author":"A Gupta","year":"2021","unstructured":"Gupta A, Badr Y, Negahban A et al (2021) Energy-efficient heating control for smart buildings with deep reinforcement learning. J Build Eng 34:1\u201335","journal-title":"J Build Eng"},{"key":"1378_CR14","doi-asserted-by":"crossref","unstructured":"Nagarathinam S, Menon V, Vasan A et al (2020) Marco-multi-agent reinforcement learning based control of building hvac systems. In: Proceedings of the eleventh ACM international conference on future energy systems, pp 57\u201367.","DOI":"10.1145\/3396851.3397694"},{"issue":"7","key":"1378_CR15","first-page":"1633","volume":"10","author":"ME Taylor","year":"2019","unstructured":"Taylor ME, Stone P (2019) Transfer learning for reinforcement learning domains: a survey. J Mach Learn Res 10(7):1633\u20131685","journal-title":"J Mach Learn Res"},{"key":"1378_CR16","doi-asserted-by":"crossref","unstructured":"Zhang X, Jin X, Tripp C et al (2020) Transferable reinforcement learning for smart homes. In: Proceedings of the 1st international workshop on reinforcement learning for energy management in buildings and cities, pp 43\u201347","DOI":"10.1145\/3427773.3427865"},{"issue":"5","key":"1378_CR17","doi-asserted-by":"publisher","first-page":"5492","DOI":"10.1109\/TSG.2018.2883701","volume":"10","author":"AY Yoon","year":"2018","unstructured":"Yoon AY, Kim YJ, Moon SI (2018) Optimal retail pricing for demand response of HVAC systems in commercial buildings considering distribution network voltages. IEEE Trans Smart Grid 10(5):5492\u20135505","journal-title":"IEEE Trans Smart Grid"},{"key":"1378_CR18","first-page":"1","volume":"3","author":"A Kumar","year":"2020","unstructured":"Kumar A, Verma A, Prakash S (2020) Ai-based building management and information system with multi-agent topology for an energy-efficient building: towards occupants comfort. IETE J Res IETE J Res 3:1\u201312","journal-title":"IETE J Res IETE J Res"},{"issue":"2","key":"1378_CR19","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1080\/03772063.2020.1838347","volume":"69","author":"A Verma","year":"2020","unstructured":"Verma A, Prakash S, Kumar A (2020) A comparative analysis of data-driven based optimization models for energy-efficient buildings. IETE J Res 69(2):796\u2013812. https:\/\/doi.org\/10.1080\/03772063.2020.1838347","journal-title":"IETE J Res"},{"key":"1378_CR20","doi-asserted-by":"publisher","unstructured":"Verma A, Prakash S, Kumar A (2021) Ann\u2010based energy consumption prediction model up to 2050 for a residential building: towards sustainable decision making. Environ Prog Susta Energy 40(3):e13544. https:\/\/doi.org\/10.1002\/ep.13544","DOI":"10.1002\/ep.13544"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-024-01378-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00607-024-01378-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-024-01378-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T02:43:52Z","timestamp":1738896232000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00607-024-01378-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,14]]},"references-count":20,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["1378"],"URL":"https:\/\/doi.org\/10.1007\/s00607-024-01378-8","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,14]]},"assertion":[{"value":"15 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The author(s) declare(s) that there are no conflicts of interest regarding the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"26"}}