{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:10:25Z","timestamp":1742998225409,"version":"3.40.3"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031440663"},{"type":"electronic","value":"9783031440670"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-44067-0_13","type":"book-chapter","created":{"date-parts":[[2023,10,20]],"date-time":"2023-10-20T06:02:33Z","timestamp":1697781753000},"page":"237-255","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Explaining Deep Reinforcement Learning-Based Methods for\u00a0Control of\u00a0Building HVAC Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4165-2633","authenticated-orcid":false,"given":"Javier","family":"Jim\u00e9nez-Raboso","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7334-1074","authenticated-orcid":false,"given":"Antonio","family":"Manjavacas","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4244-6583","authenticated-orcid":false,"given":"Alejandro","family":"Campoy-Nieves","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5688-2039","authenticated-orcid":false,"given":"Miguel","family":"Molina-Solana","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0439-3692","authenticated-orcid":false,"given":"Juan","family":"G\u00f3mez-Romero","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"key":"13_CR1","unstructured":"ASHRAE: Guideline 36\u20132021: High Performance Sequences of Operation for HVAC Systems. ASHRAE (2021)"},{"key":"13_CR2","doi-asserted-by":"publisher","first-page":"100020","DOI":"10.1016\/j.egyai.2020.100020","volume":"2","author":"D Azuatalam","year":"2020","unstructured":"Azuatalam, D., Lee, W.L., de Nijs, F., Liebman, A.: Reinforcement learning for whole-building HVAC control and demand response. Energy AI 2, 100020 (2020). https:\/\/doi.org\/10.1016\/j.egyai.2020.100020","journal-title":"Energy AI"},{"key":"13_CR3","doi-asserted-by":"publisher","unstructured":"Barredo Arrieta, A., et al.: Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion 58, 82\u2013115 (2020). https:\/\/doi.org\/10.1016\/j.inffus.2019.12.012. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1566253519308103","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"13_CR4","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-319-23461-8_1","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"E Barrett","year":"2015","unstructured":"Barrett, E., Linder, S.: Autonomous HVAC control, a reinforcement learning approach. In: Bifet, A., et al. (eds.) ECML PKDD 2015. LNCS (LNAI), vol. 9286, pp. 3\u201319. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-23461-8_1"},{"key":"13_CR5","doi-asserted-by":"publisher","unstructured":"Bastani, O., Kim, C., Bastani, H.: Interpretability via model extraction (2018). https:\/\/doi.org\/10.48550\/arXiv.1706.09773","DOI":"10.48550\/arXiv.1706.09773"},{"key":"13_CR6","doi-asserted-by":"publisher","first-page":"117164","DOI":"10.1016\/j.apenergy.2021.117164","volume":"298","author":"M Biemann","year":"2021","unstructured":"Biemann, M., Scheller, F., Liu, X., Huang, L.: Experimental evaluation of model-free reinforcement learning algorithms for continuous HVAC control. Appl. Energy 298, 117164 (2021). https:\/\/doi.org\/10.1016\/j.apenergy.2021.117164","journal-title":"Appl. Energy"},{"key":"13_CR7","doi-asserted-by":"publisher","unstructured":"Breiman, L., Friedman, J., Stone, C.J., Olshen, R.: Classification and Regression Trees. Chapman and Hall\/CRC, Wadsworth, Belmont, CA (1984). https:\/\/doi.org\/10.1201\/9781315139470","DOI":"10.1201\/9781315139470"},{"issue":"6","key":"13_CR8","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1080\/19401493.2022.2103586","volume":"15","author":"S Cho","year":"2022","unstructured":"Cho, S., Park, C.S.: Rule reduction for control of a building cooling system using explainable AI. J. Build. Perform. Simul. 15(6), 832\u2013847 (2022). https:\/\/doi.org\/10.1080\/19401493.2022.2103586","journal-title":"J. Build. Perform. Simul."},{"issue":"9","key":"13_CR9","doi-asserted-by":"publisher","first-page":"2419","DOI":"10.1007\/s10994-021-05961-4","volume":"110","author":"G Dulac-Arnold","year":"2021","unstructured":"Dulac-Arnold, G., et al.: Challenges of real-world reinforcement learning: definitions, benchmarks and analysis. Mach. Learn. 110(9), 2419\u20132468 (2021). https:\/\/doi.org\/10.1007\/s10994-021-05961-4","journal-title":"Mach. Learn."},{"key":"13_CR10","unstructured":"Dulac-Arnold, G., Mankowitz, D., Hester, T.: Challenges of real-world reinforcement learning. arXiv preprint arXiv:1904.12901 (2019)"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Fong, R.C., Vedaldi, A.: Interpretable explanations of black boxes by meaningful perturbation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.371"},{"key":"13_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2022.104165","author":"Q Fu","year":"2022","unstructured":"Fu, Q., Han, Z., Chen, J., Lu, Y., Wu, H., Wang, Y.: Applications of reinforcement learning for building energy efficiency control: a review. J. Build. Eng. (2022). https:\/\/doi.org\/10.1016\/j.jobe.2022.104165","journal-title":"J. Build. Eng."},{"key":"13_CR13","doi-asserted-by":"publisher","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1582\u20131591 (2018). https:\/\/doi.org\/10.48550\/arXiv.1802.09477","DOI":"10.48550\/arXiv.1802.09477"},{"key":"13_CR14","doi-asserted-by":"publisher","unstructured":"Geng, G., Geary, G.: On performance and tuning of PID controllers in HVAC systems. In: Proceedings of IEEE International Conference on Control and Applications, pp. 819\u2013824. IEEE (1993). https:\/\/doi.org\/10.1109\/CCA.1993.348229","DOI":"10.1109\/CCA.1993.348229"},{"key":"13_CR15","doi-asserted-by":"publisher","first-page":"38748","DOI":"10.1109\/ACCESS.2019.2906311","volume":"7","author":"J Gomez-Romero","year":"2019","unstructured":"Gomez-Romero, J., et al.: A probabilistic algorithm for predictive control with full-complexity models in non-residential buildings. IEEE Access 7, 38748\u201338765 (2019)","journal-title":"IEEE Access"},{"key":"13_CR16","unstructured":"Guo, W., Wu, X., Khan, U., Xing, X.: Edge: explaining deep reinforcement learning policies. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, pp. 12222\u201312236. Curran Associates, Inc. (2021). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/65c89f5a9501a04c073b354f03791b1f-Paper.pdf"},{"key":"13_CR17","doi-asserted-by":"publisher","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1861\u20131870. PMLR (2018). https:\/\/doi.org\/10.48550\/arXiv.1801.01290","DOI":"10.48550\/arXiv.1801.01290"},{"key":"13_CR18","doi-asserted-by":"publisher","unstructured":"Heuillet, A., Couthouis, F., D\u00edaz-Rodr\u00edguez, N.: Explainability in deep reinforcement learning. Knowl.-Based Syst. 214, 106685 (2021). https:\/\/doi.org\/10.1016\/j.knosys.2020.106685","DOI":"10.1016\/j.knosys.2020.106685"},{"key":"13_CR19","unstructured":"International Energy Agency: Tracking buildings (2021). https:\/\/www.iea.org\/reports\/tracking-buildings-2021"},{"key":"13_CR20","doi-asserted-by":"publisher","unstructured":"Jim\u00e9nez-Raboso, J., Campoy-Nieves, A., Manjavacas-Lucas, A., G\u00f3mez-Romero, J., Molina-Solana, M.: Sinergym: a building simulation and control framework for training reinforcement learning agents. In: Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, pp. 319\u2013323. Association for Computing Machinery, New York, USA (2021). https:\/\/doi.org\/10.1145\/3486611.3488729","DOI":"10.1145\/3486611.3488729"},{"key":"13_CR21","unstructured":"Juozapaitis, Z., Koul, A., Fern, A., Erwig, M., Doshi-Velez, F.: Explainable reinforcement learning via reward decomposition. In: Proceedings at the International Joint Conference on Artificial Intelligence. A Workshop on Explainable Artificial Intelligence (2019)"},{"key":"13_CR22","doi-asserted-by":"publisher","unstructured":"Krause, J., Perer, A., Ng, K.: Interacting with predictions: visual inspection of black-box machine learning models. In: Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems, pp. 5686\u20135697. CHI 2016, Association for Computing Machinery, New York, NY, USA (2016). https:\/\/doi.org\/10.1145\/2858036.2858529","DOI":"10.1145\/2858036.2858529"},{"key":"13_CR23","unstructured":"Landajuela, M., et al.: Discovering symbolic policies with deep reinforcement learning. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 139, pp. 5979\u20135989. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/landajuela21a.html"},{"key":"13_CR24","doi-asserted-by":"publisher","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015). https:\/\/doi.org\/10.48550\/arXiv.1509.02971","DOI":"10.48550\/arXiv.1509.02971"},{"key":"13_CR25","unstructured":"Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 4765\u20134774. Curran Associates, Inc. (2017). http:\/\/papers.nips.cc\/paper\/7062-a-unified-approach-to-interpreting-model-predictions.pdf"},{"key":"13_CR26","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1007\/978-3-030-30391-4_7","volume-title":"Explainable, Transparent Autonomous Agents and Multi-Agent Systems","author":"M Madhikermi","year":"2019","unstructured":"Madhikermi, M., Malhi, A.K., Fr\u00e4mling, K.: Explainable artificial intelligence based heat recycler fault detection in air handling unit. In: Calvaresi, D., Najjar, A., Schumacher, M., Fr\u00e4mling, K. (eds.) EXTRAAMAS 2019. LNCS (LNAI), vol. 11763, pp. 110\u2013125. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30391-4_7"},{"key":"13_CR27","doi-asserted-by":"publisher","unstructured":"Madumal, P., Miller, T., Sonenberg, L., Vetere, F.: Explainable reinforcement learning through a causal lens (2019). https:\/\/doi.org\/10.48550\/arXiv.1905.10958","DOI":"10.48550\/arXiv.1905.10958"},{"issue":"17","key":"13_CR28","doi-asserted-by":"publisher","first-page":"6338","DOI":"10.3390\/s22176338","volume":"22","author":"M Meas","year":"2022","unstructured":"Meas, M., et al.: Explainability and transparency of classifiers for air-handling unit faults using explainable artificial intelligence (XAI). Sensors 22(17), 6338 (2022). https:\/\/doi.org\/10.3390\/s22176338","journal-title":"Sensors"},{"key":"13_CR29","doi-asserted-by":"publisher","unstructured":"Milani, S., Topin, N., Veloso, M., Fang, F.: A survey of explainable reinforcement learning (2022). https:\/\/doi.org\/10.48550\/arXiv.2202.08434","DOI":"10.48550\/arXiv.2202.08434"},{"key":"13_CR30","doi-asserted-by":"publisher","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016). https:\/\/doi.org\/10.48550\/arXiv.1602.01783","DOI":"10.48550\/arXiv.1602.01783"},{"key":"13_CR31","doi-asserted-by":"publisher","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013). https:\/\/doi.org\/10.48550\/arXiv.1312.5602","DOI":"10.48550\/arXiv.1312.5602"},{"key":"13_CR32","doi-asserted-by":"publisher","unstructured":"Montavon, G., Lapuschkin, S., Binder, A., Samek, W., M\u00fcller, K.R.: Explaining nonlinear classification decisions with deep Taylor decomposition. Pattern Recogn. 65, 211\u2013222 (2017). https:\/\/doi.org\/10.1016\/j.patcog.2016.11.008. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320316303582","DOI":"10.1016\/j.patcog.2016.11.008"},{"key":"13_CR33","doi-asserted-by":"publisher","unstructured":"Mothilal, R.K., Sharma, A., Tan, C.: Explaining machine learning classifiers through diverse counterfactual explanations. In: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pp. 607\u2013617. FAT 2020, Association for Computing Machinery, New York, NY, USA (2020). https:\/\/doi.org\/10.1145\/3351095.3372850","DOI":"10.1145\/3351095.3372850"},{"key":"13_CR34","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1016\/j.buildenv.2019.03.062","volume":"155","author":"S Papadopoulos","year":"2019","unstructured":"Papadopoulos, S., Kontokosta, C.E., Vlachokostas, A., Azar, E.: Rethinking HVAC temperature setpoints in commercial buildings: the potential for zero-cost energy savings and comfort improvement in different climates. Build. Environ. 155, 350\u2013359 (2019). https:\/\/doi.org\/10.1016\/j.buildenv.2019.03.062","journal-title":"Build. Environ."},{"key":"13_CR35","doi-asserted-by":"publisher","unstructured":"Papernot, N., McDaniel, P.: Deep k-nearest neighbors: towards confident, interpretable and robust deep learning (2018). https:\/\/doi.org\/10.48550\/arXiv.1803.04765","DOI":"10.48550\/arXiv.1803.04765"},{"key":"13_CR36","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"13_CR37","doi-asserted-by":"publisher","unstructured":"Perera, A., Kamalaruban, P.: Applications of reinforcement learning in energy systems. Renew. Sustain. Energy Rev. 137, 110618 (2021). https:\/\/doi.org\/10.1016\/j.rser.2020.110618","DOI":"10.1016\/j.rser.2020.110618"},{"issue":"3","key":"13_CR38","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1016\/j.enbuild.2007.03.007","volume":"40","author":"L P\u00e9rez-Lombard","year":"2008","unstructured":"P\u00e9rez-Lombard, L., Ortiz, J., Pout, C.: A review on buildings energy consumption information. Energy Build. 40(3), 394\u2013398 (2008). https:\/\/doi.org\/10.1016\/j.enbuild.2007.03.007","journal-title":"Energy Build."},{"key":"13_CR39","doi-asserted-by":"publisher","unstructured":"Qing, Y., Liu, S., Song, J., Wang, H., Song, M.: A survey on explainable reinforcement learning: concepts, algorithms, challenges (2022). https:\/\/doi.org\/10.48550\/arXiv.2211.06665","DOI":"10.48550\/arXiv.2211.06665"},{"key":"13_CR40","doi-asserted-by":"publisher","unstructured":"Ribeiro, M., Singh, S., Guestrin, C.: \u201cwhy should I trust you?\u201d: explaining the predictions of any classifier. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, pp. 97\u2013101. Association for Computational Linguistics, San Diego, California (2016). https:\/\/doi.org\/10.18653\/v1\/N16-3020. https:\/\/aclanthology.org\/N16-3020","DOI":"10.18653\/v1\/N16-3020"},{"key":"13_CR41","doi-asserted-by":"publisher","unstructured":"Roth, A.M., Topin, N., Jamshidi, P., Veloso, M.: Conservative q-improvement: reinforcement learning for an interpretable decision-tree policy (2019). https:\/\/doi.org\/10.48550\/arXiv.1907.01180","DOI":"10.48550\/arXiv.1907.01180"},{"key":"13_CR42","doi-asserted-by":"publisher","unstructured":"Schulman, J., Levine, S., Moritz, P., Jordan, M.I., Abbeel, P.: Trust region policy optimization (2017). https:\/\/doi.org\/10.48550\/arXiv.1502.05477","DOI":"10.48550\/arXiv.1502.05477"},{"key":"13_CR43","doi-asserted-by":"publisher","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017). https:\/\/doi.org\/10.48550\/arXiv.1707.06347","DOI":"10.48550\/arXiv.1707.06347"},{"key":"13_CR44","doi-asserted-by":"publisher","unstructured":"Shapley, L.S.: A Value for n-Person Games, pp. 307\u2013318. Princeton University Press, Princeton (1953). https:\/\/doi.org\/10.1515\/9781400881970-018","DOI":"10.1515\/9781400881970-018"},{"issue":"2","key":"13_CR45","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1109\/TSG.2020.3035127","volume":"12","author":"H Shuai","year":"2021","unstructured":"Shuai, H., He, H.: Online scheduling of a residential microgrid via Monte-Carlo tree search and a learned model. IEEE Trans. Smart Grid 12(2), 1073\u20131087 (2021). https:\/\/doi.org\/10.1109\/TSG.2020.3035127","journal-title":"IEEE Trans. Smart Grid"},{"key":"13_CR46","doi-asserted-by":"publisher","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018). https:\/\/doi.org\/10.1109\/tnn.1998.712192","DOI":"10.1109\/tnn.1998.712192"},{"key":"13_CR47","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., et al.: Energy optimization associated with thermal comfort and indoor air control via a deep reinforcement learning algorithm. Build. Environ. 155, 105\u2013117 (2019)","journal-title":"Build. Environ."},{"key":"13_CR48","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.scs.2018.11.021","volume":"45","author":"JR V\u00e1zquez-Canteli","year":"2019","unstructured":"V\u00e1zquez-Canteli, J.R., Ulyanin, S., K\u00e4mpf, J., Nagy, Z.: Fusing TensorFlow with building energy simulation for intelligent energy management in smart cities. Sustain. Urban Areas 45, 243\u2013257 (2019). https:\/\/doi.org\/10.1016\/j.scs.2018.11.021","journal-title":"Sustain. Urban Areas"},{"key":"13_CR49","doi-asserted-by":"publisher","unstructured":"Vouros, G.A.: Explainable deep reinforcement learning: state of the art and challenges. ACM Comput. Surv. 55(5), 92:1\u201392:39 (2022). https:\/\/doi.org\/10.1145\/3527448","DOI":"10.1145\/3527448"},{"issue":"3\u20134","key":"13_CR50","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJ Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"issue":"6","key":"13_CR51","doi-asserted-by":"publisher","first-page":"2586","DOI":"10.1109\/TCST.2020.3047407","volume":"29","author":"Y Yang","year":"2021","unstructured":"Yang, Y., Srinivasan, S., Hu, G., Spanos, C.J.: Distributed control of multizone HVAC systems considering indoor air quality. IEEE Trans. Control Syst. Technol. 29(6), 2586\u20132597 (2021). https:\/\/doi.org\/10.1109\/TCST.2020.3047407","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"13_CR52","doi-asserted-by":"publisher","unstructured":"Yao, Y., Shekhar, D.K.: State of the art review on model predictive control (MPC) in heating ventilation and air-conditioning (HVAC) field. Build. Environ. 200, 107952 (2021). https:\/\/doi.org\/10.1016\/j.buildenv.2021.107952","DOI":"10.1016\/j.buildenv.2021.107952"},{"key":"13_CR53","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3078462","author":"L Yu","year":"2021","unstructured":"Yu, L., Qin, S., Zhang, M., Shen, C., Jiang, T., Guan, X.: A review of deep reinforcement learning for smart building energy management. IEEE Internet Things J. (2021). https:\/\/doi.org\/10.1109\/JIOT.2021.3078462","journal-title":"IEEE Internet Things J."},{"issue":"2","key":"13_CR54","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1109\/TCSS.2021.3096824","volume":"9","author":"K Zhang","year":"2022","unstructured":"Zhang, K., Zhang, J., Xu, P.D., Gao, T., Gao, D.W.: Explainable AI in deep reinforcement learning models for power system emergency control. IEEE Trans. Comput. Soc. Syst. 9(2), 419\u2013427 (2022). https:\/\/doi.org\/10.1109\/TCSS.2021.3096824","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"13_CR55","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1016\/j.enbuild.2019.07.029","volume":"199","author":"Z Zhang","year":"2019","unstructured":"Zhang, Z., Chong, A., Pan, Y., Zhang, C., Lam, K.P.: Whole building energy model for HVAC optimal control: a practical framework based on deep reinforcement learning. Energy Build. 199, 472\u2013490 (2019)","journal-title":"Energy Build."},{"issue":"3","key":"13_CR56","doi-asserted-by":"publisher","first-page":"52","DOI":"10.3390\/designs6030052","volume":"6","author":"X Zhong","year":"2022","unstructured":"Zhong, X., Zhang, Z., Zhang, R., Zhang, C.: End-to-end deep reinforcement learning control for HVAC systems in office buildings. Designs 6(3), 52 (2022). https:\/\/doi.org\/10.3390\/designs6030052","journal-title":"Designs"}],"container-title":["Communications in Computer and Information Science","Explainable Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44067-0_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:05:04Z","timestamp":1707804304000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44067-0_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031440663","9783031440670"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44067-0_13","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"21 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"xAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"World Conference on Explainable Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"xai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/xaiworldconference.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"220","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"94","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"43% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}