{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T07:02:28Z","timestamp":1780729348269,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819214617","type":"print"},{"value":"9789819214624","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-92-1462-4_14","type":"book-chapter","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:48:31Z","timestamp":1780728511000},"page":"171-183","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Meta-RL with Shared Representations Enables Fast Adaptation in Energy Systems"],"prefix":"10.1007","author":[{"given":"Th\u00e9o","family":"Zangato","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aomar","family":"Osmani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pegah","family":"Alizadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,7]]},"reference":[{"key":"14_CR1","unstructured":"Andrychowicz, M., et al.: What matters for on-policy deep actor-critic methods? A large-scale study. In: ICLR (2021)"},{"key":"14_CR2","unstructured":"Beck, J., et al.: A survey of meta-reinforcement learning. CoRR arXiv:2301.08028 (2023)"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Qu, G., Tang, Y., Low, S., Li, N.: Reinforcement learning for selective key applications in power systems: recent advances and future challenges. IEEE Trans. Smart Grid (2022)","DOI":"10.1109\/TSG.2022.3154718"},{"key":"14_CR4","unstructured":"Cobbe, K.W., Hilton, J., Klimov, O., Schulman, J.: Phasic policy gradient. In: ICML, pp. 2020\u20132027. PMLR (2021)"},{"key":"14_CR5","unstructured":"Duan, Y., Schulman, J., Chen, X., Bartlett, P.L., Sutskever, I., Abbeel, P.: Rl$$^2$$: fast reinforcement learning via slow reinforcement learning. arXiv preprint arXiv:1611.02779 (2016)"},{"key":"14_CR6","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: ICML, pp. 1126\u20131135. PMLR (2017)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Jose, S.T., Simeone, O.: An information-theoretic analysis of the impact of task similarity on meta-learning. In: 2021 IEEE ISIT, pp. 1534\u20131539. IEEE (2021)","DOI":"10.1109\/ISIT45174.2021.9517767"},{"key":"14_CR8","unstructured":"Kirsch, L., van Steenkiste, S., Schmidhuber, J.: Improving generalization in meta reinforcement learning using learned objectives. In: ICLR (2020)"},{"issue":"18","key":"14_CR9","doi-asserted-by":"publisher","first-page":"7727","DOI":"10.3390\/su12187727","volume":"12","author":"K Kurte","year":"2020","unstructured":"Kurte, K., et al.: Evaluating the adaptability of reinforcement learning based HVAC control for residential houses. Sustainability 12(18), 7727 (2020)","journal-title":"Sustainability"},{"key":"14_CR10","unstructured":"Mitchell, E., Rafailov, R., Peng, X.B., Levine, S., Finn, C.: Offline meta-reinforcement learning with advantage weighting. In: ICML. PMLR (2021)"},{"key":"14_CR11","unstructured":"Nichol, A., Achiam, J., Schulman, J.: On first-order meta-learning algorithms. CoRR arXiv:1803.02999 (2018)"},{"key":"14_CR12","unstructured":"Peng, M., Zhu, B., Jiao, J.: Linear representation meta-reinforcement learning for instant adaptation. arXiv preprint arXiv:2101.04750 (2021)"},{"key":"14_CR13","unstructured":"Rakelly, K., Zhou, A., Finn, C., Levine, S., Quillen, D.: Efficient off-policy meta-reinforcement learning via probabilistic context variables. In: ICML, pp. 5331\u20135340. PMLR (2019)"},{"key":"14_CR14","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR arXiv:1707.06347 (2017)"},{"issue":"10","key":"14_CR15","doi-asserted-by":"publisher","first-page":"2367","DOI":"10.3390\/en17102367","volume":"17","author":"H Shen","year":"2024","unstructured":"Shen, H., Shen, X., Chen, Y.: Real-time microgrid energy scheduling using meta-reinforcement learning. Energies 17(10), 2367 (2024)","journal-title":"Energies"},{"key":"14_CR16","unstructured":"Sung, F., Zhang, L., Xiang, T., Hospedales, T.M., Yang, Y.: Learning to learn: meta-critic networks for sample efficient learning. CoRR arXiv:1706.09529 (2017)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"V\u00e1zquez-Canteli, J.R., K\u00e4mpf, J., Henze, G., Nagy, Z.: Citylearn v1.0: an OpenAI gym environment for demand response with deep reinforcement learning. In: Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, pp. 356\u2013357 (2019)","DOI":"10.1145\/3360322.3360998"},{"issue":"4","key":"14_CR18","first-page":"1685","volume":"70","author":"L Xiong","year":"2023","unstructured":"Xiong, L., et al.: Meta-reinforcement learning-based transferable scheduling strategy for energy management. IEEE Trans. Circ. Syst. 70(4), 1685\u20131695 (2023)","journal-title":"IEEE Trans. Circ. Syst."},{"key":"14_CR19","unstructured":"Xu, Z., van Hasselt, H.P., Silver, D.: Meta-gradient reinforcement learning. In: NIPS, vol. 31 (2018)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Young, K., Wang, B., Taylor, M.E.: Metatrace actor-critic: online step-size tuning by meta-gradient descent for reinforcement learning control. In: IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/581"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Zangato, T., Osmani, A., Alizadeh, P.: Enhancing decision-making in energy management systems through action-independent dynamics learning. In: ECAI 2024, pp. 4571\u20134578. IOS Press (2024)","DOI":"10.3233\/FAIA241050"},{"key":"14_CR22","doi-asserted-by":"publisher","first-page":"1888","DOI":"10.1016\/j.egyr.2025.01.002","volume":"13","author":"T Zangato","year":"2025","unstructured":"Zangato, T., Osmani, A., Alizadeh, P.: Data-driven policy mapping for safe RL-based energy management systems. Energy Rep. 13, 1888\u20131909 (2025)","journal-title":"Energy Rep."},{"key":"14_CR23","unstructured":"Zhang, H., Wu, D., Boulet, B.: Metaems: a meta reinforcement learning-based control framework for building energy management system. CoRR arXiv:2210.12590 (2022)"},{"key":"14_CR24","unstructured":"Zintgraf, L., Shiarli, K., Kurin, V., Hofmann, K., Whiteson, S.: Fast context adaptation via meta-learning. In: ICML, pp. 7693\u20137702. PMLR (2019)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-1462-4_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T06:48:34Z","timestamp":1780728514000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-1462-4_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819214617","9789819214624"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-1462-4_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"7 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}