{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:56:05Z","timestamp":1743094565458,"version":"3.40.3"},"publisher-location":"Cham","reference-count":76,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031390586"},{"type":"electronic","value":"9783031390593"}],"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\/978-3-031-39059-3_26","type":"book-chapter","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T13:01:37Z","timestamp":1690722097000},"page":"385-402","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Survey on Reinforcement Learning and Deep Reinforcement Learning for Recommender Systems"],"prefix":"10.1007","author":[{"given":"Mehrdad","family":"Rezaei","sequence":"first","affiliation":[]},{"given":"Nasseh","family":"Tabrizi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,31]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Kla\u0161nja-Mili\u0107evi\u0107, A., Ivanovi\u0107, M., Nanopoulos, A.: Recommender systems in e-learning environments: a survey of the state of the art and possible extensions. Artif. Intell. Rev. 44(4), 571\u2013604 (2015)","DOI":"10.1007\/s10462-015-9440-z"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Schafer, J.B., Konstan, J., Riedl, J.: Recommender systems in e-commerce. In: ACM Conference on Electronic Commerce, pp. 158\u2013166 (1999)","DOI":"10.1145\/336992.337035"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Sezgin, E., Ozkan, S.: A systematic literature review on health recommender systems. In: E-Health and Bioengineering Conference (EHB), pp. 1\u20134. IEEE (2013)","DOI":"10.1109\/EHB.2013.6707249"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Karimi, M., Jannach, D., Jugovac, M.: News recommender systems survey and roads ahead. Inf. Process. Manag. 54(6), 1203\u20131227 (2018)","DOI":"10.1016\/j.ipm.2018.04.008"},{"key":"26_CR5","doi-asserted-by":"publisher","unstructured":"Ricci, F., Rokach, L., Shapira, B.: Introduction to Recommender Systems Handbook. In: Ricci, F., Rokach, L., Shapira, B., Kantor, P. (eds.) Recommender Systems Handbook, pp. 1\u201335. Springer, Boston, MA (2011). https:\/\/doi.org\/10.1007\/978-0-387-85820-3_1","DOI":"10.1007\/978-0-387-85820-3_1"},{"issue":"1","key":"26_CR6","first-page":"1","volume":"52","author":"S Zhang","year":"2019","unstructured":"Zhang, S., Yao, L., Sun, A., Tay, Y.: Deep learning based recommender system: a survey and new perspectives. Comput. Surv. (CSUR) 52(1), 1\u201338 (2019)","journal-title":"Comput. Surv. (CSUR)"},{"issue":"11","key":"26_CR7","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Jens Kober","year":"2013","unstructured":"Jens Kober, J., Bagnell, A., Peters, J.: Reinforcement learning in robotics: a survey. J. Robot. Res. 32(11), 1238\u20131274 (2013)","journal-title":"J. Robot. Res."},{"key":"26_CR8","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.procir.2017.03.095","volume":"63","author":"R Meyes","year":"2017","unstructured":"Meyes, R., et al.: Motionplanning for industrial robots using reinforcement learning. Procedia CIRP 63, 107\u2013112 (2017)","journal-title":"Procedia CIRP"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Navaei, M., Tabrizi, N.: Machine learning in software development life cycle: a comprehensive review. ENASE, pp. 344\u2013354 (2022)","DOI":"10.5220\/0011040600003176"},{"issue":"19","key":"26_CR10","doi-asserted-by":"publisher","first-page":"70","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023","volume":"2017","author":"AEL Sallab","year":"2017","unstructured":"Sallab, A.E.L., Abdou, M., Perot, E., Yogamani, S.: Deep reinforcement learning framework autonomous driving. Electron. Imaging 2017(19), 70\u201376 (2017)","journal-title":"Electron. Imaging"},{"key":"26_CR11","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.robot.2019.01.003","volume":"114","author":"C You","year":"2019","unstructured":"You, C., Jianbo, L., Filev, D., Tsiotras, P.: Advanced planning for autonomous vehicles using reinforcement learning and deep inverse reinforcement learning. Robot. Auton. Syst. 114, 118 (2019)","journal-title":"Robot. Auton. Syst."},{"key":"26_CR12","unstructured":"Jiang, Z., Xu, D., Liang, J.: A deep reinforcement learning framework for the financial portfolio management problem (2017). arXiv"},{"key":"26_CR13","unstructured":"Guez, A., Vincent, R.D., Avoli, M., Pineau, J.: Adaptive treatment of epilepsy via batch-mode reinforcement learning. In: AAAI, pp. 1671\u20131678 (2008)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Chen, M., Beutel, A., Covington, P., Jain, S., Belletti, F., Chi, E.H.: Top-k off policy correction for a reinforce recommender system. In: ACM International Conference on Web Search and Data Mining, pp. 456\u2013464 (2019)","DOI":"10.1145\/3289600.3290999"},{"key":"26_CR15","doi-asserted-by":"crossref","unstructured":"Smyth, B., Cotter, P.: A personalised TV listings service for the digital TV age. Knowl.-Based Syst. (2000)","DOI":"10.1016\/S0950-7051(00)00046-0"},{"key":"26_CR16","unstructured":"Singh, S., Kearns, M., Litman, D., Walker, M.: Reinforcement learning for spoken dialogue systems. Neural Inf. Process. Syst. 956\u2013962 (2000)"},{"key":"26_CR17","unstructured":"Tetreault, J., Litman, D.: Using reinforcement learning to build a better model of dialogue state. In: European Chapter of the Association for Computational Linguistics (2006)"},{"key":"26_CR18","unstructured":"Sutton, R.S., Bartom, A.G.: Introduction to Reinforcement Learning, vol. 2. MIT Press, Cambridge (2017)"},{"key":"26_CR19","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards (1989)"},{"key":"26_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Image net classification with deep convolutional neural networks. Neural Inf. Process. Syst. 1097\u20131105 (2012)"},{"issue":"12","key":"26_CR21","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1145\/138859.138867","volume":"35","author":"D Goldberg","year":"1992","unstructured":"Goldberg, D., Nichols, D., Terry, D., Oki, B.M.: Using collaborative filtering to weave an information tapestry. ACM 35(12), 61\u201370 (1992)","journal-title":"ACM"},{"key":"26_CR22","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning (2015). arXiv"},{"key":"26_CR23","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In International Conference on Machine Learning (2016)"},{"key":"26_CR24","unstructured":"Shani, G., Heckerman, D., Brafman, R.I., Boutilier, C.: An MDP based recommender system. Mach. Learn. Res. J. 6(Sep), 1265\u20131295 (2005)"},{"key":"26_CR25","unstructured":"Dulac-Arnold, G., et al.:"},{"key":"26_CR26","unstructured":"Joachims, T., Freitag, D., Mitchell, T.: Webwatcher: a tour guide for the world wide web. In: IJCAI (1), pp. 770\u2013777. Citeseer (1997)"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Srivihok, A., Sukonmanee, P.: Ecommerce intelligent agent: personalization travel support agent using Q learning. In: 7th International Conference on Electronic Commerce, pp. 287\u2013292 (2005)","DOI":"10.1145\/1089551.1089606"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Taghipour, N., Kardan, A., Ghidary, S.S.: Usage based web recommendations: a reinforcement learning approach. In: ACM Conference on Recommender Systems, pp. 113\u2013120 (2007)","DOI":"10.1145\/1297231.1297250"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Mobasher, B., Cooley, R., Srivastava, J.: Automatic personalization based on web usage mining. ACM 43(8), 142\u2013151 (2000)","DOI":"10.1145\/345124.345169"},{"key":"26_CR30","unstructured":"Thomas, P.S., Theocharous, G. Rojanavasu, P., Srinil, P., Pinngern, O.: New recommendation systemusing reinforcement learning. Spec. Issue Int. J. Comput. Internet Manag. 13(SP 3) (2005)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Intayoad, W., Kamyod, C., Temdee, P.: Reinforcement learning for online learning recommendation system. In: 2018 Global Wireless Summit (GWS), pp. 167\u2013170. IEEE (2018)","DOI":"10.1109\/GWS.2018.8686513"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Chi, C.Y., Tsai, R.T.H., Lai, J.Y., Hsu, J.Y.J.: A reinforcement learning approach to emotion-based automatic playlist generation. In: 2010 International Conference on Technologies and Applications of Artificial Intelligence, pp. 60\u201365. IEEE (2010)","DOI":"10.1109\/TAAI.2010.21"},{"key":"26_CR33","unstructured":"Choi, S., Ha, H., Hwang, U., Kim, C., Ha, J.W., Yoon, S.: Reinforcement learning based recommender system using biclustering technique (2018). arXiv preprint arXiv:1801.05532"},{"key":"26_CR34","doi-asserted-by":"crossref","unstructured":"Prelic, A., et al.: A systematic comparison and evaluation of biclustering methods for gene expression data. Bioinformatics 22(9), 1122\u20131129 (2006)","DOI":"10.1093\/bioinformatics\/btl060"},{"key":"26_CR35","doi-asserted-by":"crossref","unstructured":"Rodriguez-Baena, D.S., Perez-Pulido, A.J., Aguilar-Ruiz, J.S.: A biclustering algorithm for extracting bit-patterns from binary datasets. Bioinformatics 27(19), 2738\u20132745 (2011)","DOI":"10.1093\/bioinformatics\/btr464"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Bohnenberger, T., Jameson, A.: When policies are better than plans: decision theoretic planning of recommendation sequences. In: International Conference on Intelligent User Interfaces, pp. 21\u201324 (2001)","DOI":"10.1145\/359784.359829"},{"key":"26_CR37","unstructured":"Liebman, E., Saar-Tsechansky, M., Stone, P.: Dj-mc: a reinforcement earning agent for music playlist recommendation (2014). arXiv"},{"issue":"1","key":"26_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13638-019-1619-6","volume":"2019","author":"F Qi","year":"2019","unstructured":"Qi, F., Tong, X., Yu, L., Wang, Y.: Personalized project recommendations: using reinforcement learning. EURASIP J. Wirel. Commun. Netw. 2019(1), 1\u201317 (2019). https:\/\/doi.org\/10.1186\/s13638-019-1619-6","journal-title":"EURASIP J. Wirel. Commun. Netw."},{"key":"26_CR39","doi-asserted-by":"publisher","unstructured":"Wang, Y.: A hybrid recommendation for music based on reinforcement learning. In: Lauw, H., Wong, R.W., Ntoulas, A., Lim, E.P., Ng, S.K., Pan, S. (eds.) Advances in Knowledge Discovery and Data Mining. PAKDD 2020. LNCS, vol. 12084, pp. 91\u2013103. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-47426-3_8","DOI":"10.1007\/978-3-030-47426-3_8"},{"key":"26_CR40","doi-asserted-by":"publisher","unstructured":"Zou, L., Xia, L., Ding, Z., Yin, D., Song, J., Liu, W.: Reinforcement learning to diversify Top-N recommendation. In: Li, G., Yang, J., Gama, J., Natwichai, J., Tong, Y. (eds.) Database Systems for Advanced Applications. DASFAA 2019. LNCS, vol. 11447, pp. 104\u2013120. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-18579-4_7","DOI":"10.1007\/978-3-030-18579-4_7"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Zeng, D., Socinski, M.A., Kosorok, M.R.: Reinforcement learning strategies forclinical trials in nonsmall cell lung cancer (2011)","DOI":"10.1111\/j.1541-0420.2011.01572.x"},{"issue":"1\u20132","key":"26_CR42","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s10994-010-5229-0","volume":"84","author":"SM Shortreed","year":"2011","unstructured":"Shortreed, S.M., Laber, E., Lizotte, D.J., Scott Stroup, T., Pineau, J., Murphy, S.A.: Informing sequential clinical decision making through reinforcement learning: an empirical study. Mach. Learn. 84(1\u20132), 109\u2013136 (2011)","journal-title":"Mach. Learn."},{"key":"26_CR43","doi-asserted-by":"crossref","unstructured":"Theocharous, G., Thomas, P.S., Ghavamzadeh, M.: Personalized ad recommendation systems for lifetime value optimization with guarantees. In: Twenty-Fourth International Joint Conference on Artificial Intelligence (2015)","DOI":"10.1145\/2740908.2741998"},{"key":"26_CR44","unstructured":"Vapnik, V.: The Nature of Statistical Learning Theory. Springer science & business media (2013)"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Little, R.J.A., Rubin, D.B.: Statistical Analysis with Missing Data, vol. 793. John Wiley, Hoboken (2019)","DOI":"10.1002\/9781119482260"},{"key":"26_CR46","unstructured":"Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. J. Mach. Learn. Res. 6(Apr), 503\u201356 (2005)"},{"key":"26_CR47","unstructured":"Sunehag, P., Evans, R., Dulac-Arnold, G., Zwols, Y., Visentin, D., Coppin, B.: Deep reinforcement learning with attention for slate Markov decision processes with high dimensional states and actions (2015). arXiv preprint arXiv:1512.01124"},{"key":"26_CR48","unstructured":"Ie, E., et al.: Reinforcement learning for slate-based recommender systems: a tractable decomposition and practical methodology (2019). arXiv preprint arXiv:1905.12767"},{"key":"26_CR49","doi-asserted-by":"crossref","unstructured":"Nemati, S., Ghassemi, M.M., Clifford, G.D.: Optimal medication dosing fromsuboptimal clinical examples: a deep reinforcementlearning approach. Eng. Med. Biol. Soc. 2978\u20132981. IEEE (2016)","DOI":"10.1109\/EMBC.2016.7591355"},{"key":"26_CR50","unstructured":"Raghu, A., Komorowski, M., Ahmed, I., Celi, L., Szolovits, P., Ghassemi, M.: Deep reinforcement learning for sepsis treatment (2017). arXiv preprint arXiv:1711.09602"},{"key":"26_CR51","unstructured":"Chen, X., Li, S., Li, H., Jiang, S., Qi, Y., Song, L.: Generative adversarial user model for reinforcement learning based recommendation system. In: International Conference on Machine Learning, pp. 1052\u20131061 (2019)"},{"key":"26_CR52","doi-asserted-by":"crossref","unstructured":"Chen, S.Y., Yu, Y., Da, Q., Tan, J., Huang, H.K., Tang, H.H.: Stabilizing reinforcement learning in dynamic environment with application to online recommendation. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2018)","DOI":"10.1145\/3219819.3220122"},{"key":"26_CR53","doi-asserted-by":"crossref","unstructured":"Yuyan, Z., Xiayao, S., Yong, L.: A novel movie recommendation system based on deep reinforcement learning with prioritized experience replay. In: 2019 IEEE 19th International Conference on Communication Technology (ICCT), pp. 1496\u20131500. IEEE (2019)","DOI":"10.1109\/ICCT46805.2019.8947012"},{"key":"26_CR54","unstructured":"Zhao, X., Xia, L., Yin, D., Tang, J.: Model-based reinforcement learning for wholechain recommendations (2019). arXiv preprint arXiv:1902.03987"},{"key":"26_CR55","unstructured":"Casanueva, I., et al.: Deep reinforcement learning for recommender systems. In: 2018 International Conference on Information and Communications Technology (icoiact), pp. 226\u2013233. IEEE (2018)"},{"key":"26_CR56","unstructured":"Hinton, G.E., Sabour, S., Frosst, N.: Matrix capsules with EM routing. In: International Conference on Learning Representations (2018)"},{"key":"26_CR57","doi-asserted-by":"publisher","unstructured":"Zhao, C., Hu, L.: CapDRL: a deep capsule reinforcement learning for movie recommendation. In: Nayak, A., Sharma, A. (eds.) PRICAI 2019: Trends in Artificial Intelligence. PRICAI 2019. LNCS, vol. 11672, pp. 734\u2013739. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-29894-4_59","DOI":"10.1007\/978-3-030-29894-4_59"},{"key":"26_CR58","doi-asserted-by":"publisher","unstructured":"Greco, C., Suglia, A., Basile, P., Semeraro, G.: Converse-et-impera: exploiting deep learning and hierarchical reinforcement learning for conversational recommender systems. In: Esposito, F., Basili, R., Ferilli, S., Lisi, F. (eds.) AI*IA 2017 Advances in Artificial Intelligence. AI*IA 2017. LNCS, vol. 10640, pp. 372\u2013386. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-70169-1_28","DOI":"10.1007\/978-3-319-70169-1_28"},{"key":"26_CR59","unstructured":"Kulkarni, T.D., Narasimhan, K., Saeedi, A., Tenenbaum, J.: Hierarchical deep reinforcement learning: integrating temporal abstraction and intrinsic motivation. Neural Inf. Process. Syst. 3675\u20133683 (2016)"},{"key":"26_CR60","doi-asserted-by":"crossref","unstructured":"Liang, H.: Drprofling: deep reinforcement user pro\u2000ling for recommendations in heterogenous information networks. IEEE Knowl. Data Eng. (2020)","DOI":"10.1109\/TKDE.2020.2998695"},{"key":"26_CR61","doi-asserted-by":"crossref","unstructured":"Liu, S., Chen, Y., Huang, H., Xiao, L., Hei, X.: Towards smart educational recommendations with reinforcement learning in classroom. In: International Conference on Teaching, Assessment, and Learning for Engineering, pp. 1079\u20131084. IEEE (2018)","DOI":"10.1109\/TALE.2018.8615217"},{"key":"26_CR62","doi-asserted-by":"crossref","unstructured":"Den Hengst, F., Hoogendoorn, M., Van Harmelen, F., Bosman, J.: Reinforcement learning for personalized dialogue management. In: International Conference on Web Intelligence (2019)","DOI":"10.1145\/3350546.3352501"},{"key":"26_CR63","doi-asserted-by":"publisher","unstructured":"Fotopoulou, E., Zafeiropoulos, A., Feidakis, M., Metafas, D., Papavassiliou, S.: An interactive recommender system based on reinforcement learning for improving emotional competences in educational groups. In: Kumar, V., Troussas, C. (eds.) Intelligent Tutoring Systems. ITS 2020. LNCS, vol. 12149, pp. 248\u2013258. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-49663-0_29","DOI":"10.1007\/978-3-030-49663-0_29"},{"key":"26_CR64","doi-asserted-by":"crossref","unstructured":"Mahmood, T., Ricci, F.: Learning and adaptivity in interactive recommender systems. In: Conference on Electronic Commerce, pp. 75\u201384 (2007)","DOI":"10.1145\/1282100.1282114"},{"key":"26_CR65","doi-asserted-by":"crossref","unstructured":"Preda, M., Popescu, D.: Personalized web recommendations: supporting epistemic information about end-users. In: The 2005 IEEE\/WIC\/ACM International Conference on Web Intelligence (WI\u201905), pp. 692\u2013695. IEEE (2005)","DOI":"10.1109\/WI.2005.115"},{"issue":"3\u20134","key":"26_CR66","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/BF00992699","volume":"8","author":"L-J Lin","year":"1992","unstructured":"Lin, L.-J.: Self-improving reactive agents based on reinforcement learning, planning and teaching. Mach. Learn. 8(3\u20134), 293\u2013321 (1992)","journal-title":"Mach. Learn."},{"key":"26_CR67","unstructured":"Thrun, S., Schwartz, A.: Issues in using function approximation for reinforcement learning. Connectionist Models Summer School Hillsdale. Lawrence Erlbaum, NJ (1993)"},{"key":"26_CR68","doi-asserted-by":"crossref","unstructured":"Yu, T., Shen, Y., Zhang, R., Zeng, X., Jin, H.: Vision-language recommendation via attribute augmented multimodal reinforcement learning. In: ACM International Conference on Multimedia, pp. 39\u201347 (2019)","DOI":"10.1145\/3343031.3350935"},{"key":"26_CR69","doi-asserted-by":"crossref","unstructured":"Xian, Y., Fu, Z., Muthukrishnan, S., De Melo, G., Zhang, Y.: Reinforcement knowledge graph reasoning for explainable recommendation. In: ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 285\u2013294 (2019)","DOI":"10.1145\/3331184.3331203"},{"key":"26_CR70","unstructured":"Zhang, Y., Chen, X.: Explainable recommendation: a survey and new perspectives (2018). arXiv:1804.11192"},{"key":"26_CR71","doi-asserted-by":"crossref","unstructured":"Cosley, D., Lam, S.K., Albert, I., Konstan, J.A., Riedl, J.: Is seeing believing how recommender system interfaces a\u2000ect users\u2019 opinions. In: Conference on Human Factors in Computing Systems, pp. 585\u2013592 (2003)","DOI":"10.1145\/642611.642713"},{"key":"26_CR72","doi-asserted-by":"crossref","unstructured":"Chen, L., Pu, P.: Trust building in recommender agents workshop on web personalization, Recommender Systems and Intelligent User Interfaces at the 2nd International Conference on E-Business, pp. 135\u2013145. Citeseer (2005)","DOI":"10.5220\/0001422901350145"},{"key":"26_CR73","doi-asserted-by":"crossref","unstructured":"Tintarev, N., Mastho, J.: Exective explanations of recommendations: usercentered design. In: ACM Conference on Recommender Systems, pp. 153\u2013156 (2007)","DOI":"10.1145\/1297231.1297275"},{"issue":"3","key":"26_CR74","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/3236386.3241340","volume":"16","author":"ZC Lipton","year":"2018","unstructured":"Lipton, Z.C.: The mythos of model interpretability. Queue 16(3), 31\u201357 (2018)","journal-title":"Queue"},{"key":"26_CR75","doi-asserted-by":"crossref","unstructured":"Wang, X., Chen, Y., Yang, J., Wu, L., Wu, Z., Xie, X.: A reinforcement learning framework for explainable recommendation. In: Conference on Data Mining, pp. 587\u2013596. IEEE (2018)","DOI":"10.1109\/ICDM.2018.00074"},{"key":"26_CR76","doi-asserted-by":"crossref","unstructured":"Barto, A.G.: Reinforcement learning and dynamic programming. In: Analysis, Design and Evaluation of Man Machine Systems, pp. 407\u2013412. Elsevier (1995)","DOI":"10.1016\/B978-0-08-042370-8.50010-0"}],"container-title":["Communications in Computer and Information Science","Deep Learning Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-39059-3_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T09:19:19Z","timestamp":1729847959000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-39059-3_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031390586","9783031390593"],"references-count":76,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-39059-3_26","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":"31 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DeLTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Deep Learning Theory and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"13 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"delta2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/delta.scitevents.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"42","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":"9","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":"22","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":"21% - 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":"4","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)"}}]}}