{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T01:25:54Z","timestamp":1769822754034,"version":"3.49.0"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T00:00:00Z","timestamp":1684972800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T00:00:00Z","timestamp":1684972800000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1007\/s11042-023-15361-6","type":"journal-article","created":{"date-parts":[[2023,5,25]],"date-time":"2023-05-25T08:02:07Z","timestamp":1685001727000},"page":"6161-6182","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Promoting human-AI interaction makes a better adoption of deep reinforcement learning: a real-world application in game industry"],"prefix":"10.1007","volume":"83","author":[{"given":"Zhipeng","family":"Hu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8998-1217","authenticated-orcid":false,"given":"Haoyu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Xiong","sequence":"additional","affiliation":[]},{"given":"Lizi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Runze","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Guan","sequence":"additional","affiliation":[]},{"given":"Yujing","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Tangjie","family":"Lyu","sequence":"additional","affiliation":[]},{"given":"Changjie","family":"Fan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,25]]},"reference":[{"issue":"20","key":"15361_CR1","doi-asserted-by":"publisher","first-page":"30939","DOI":"10.1007\/s11042-021-11306-z","volume":"80","author":"H Agius","year":"2021","unstructured":"Agius H, Daylamani-Zad D (2021) Guest editorial: interaction in immersive experiences. Multimed Tools Appl 80(20):30939\u201330942","journal-title":"Multimed Tools Appl"},{"key":"15361_CR2","doi-asserted-by":"crossref","unstructured":"Amershi S, Fogarty J, Weld D (2012) Regroup: Interactive machine learning for on-demand group creation in social networks. In: Proceedings of the SIGCHI conference on human factors in computing systems, pp 21\u201330","DOI":"10.1145\/2207676.2207680"},{"key":"15361_CR3","unstructured":"Amir D, Amir O (2018) Highlights: summarizing agent behavior to people. In: Proceedings of the 17th international conference on autonomous agents and multiagent systems, pp 1168\u20131176"},{"key":"15361_CR4","doi-asserted-by":"crossref","unstructured":"Anderson A, Dodge J, Sadarangani A et al (2019) Explaining reinforcement learning to mere mortals: an empirical study. In: Proceedings of the 28th international joint conference on artificial intelligence, pp 1328\u20131334","DOI":"10.24963\/ijcai.2019\/184"},{"key":"15361_CR5","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"AB Arrieta","year":"2020","unstructured":"Arrieta A B, D\u00edaz-rodr\u00edguez N, Del Ser J et al (2020) Explainable artificial intelligence (xai): concepts, taxonomies, opportunities and challenges toward responsible ai. Inf Fusion 58:82\u2013115","journal-title":"Inf Fusion"},{"issue":"6","key":"15361_CR6","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"K Arulkumaran","year":"2017","unstructured":"Arulkumaran K, Deisenroth M P, Brundage M et al (2017) Deep reinforcement learning: a brief survey. IEEE Signal Proc Mag 34(6):26\u201338","journal-title":"IEEE Signal Proc Mag"},{"key":"15361_CR7","unstructured":"Berner C, Brockman G, Chan B et al (2019) Dota 2 with large scale deep reinforcement learning. arXiv:191206680"},{"key":"15361_CR8","doi-asserted-by":"crossref","unstructured":"Bhatt U, Xiang A, Sharma S et al (2020) Explainable machine learning in deployment. In: Proceedings of the 2020 conference on fairness, accountability, and transparency, pp 648\u2013657","DOI":"10.1145\/3351095.3375624"},{"key":"15361_CR9","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00058655","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman L (1996) Bagging predictors. Mach Learn 24:123\u2013140","journal-title":"Mach Learn"},{"issue":"1","key":"15361_CR10","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/s11042-010-0660-6","volume":"51","author":"J Carmigniani","year":"2011","unstructured":"Carmigniani J, Furht B, Anisetti M et al (2011) Augmented reality technologies, systems and applications. Multimed Tools Appl 51(1):341\u2013377","journal-title":"Multimed Tools Appl"},{"issue":"9","key":"15361_CR11","doi-asserted-by":"publisher","first-page":"5501","DOI":"10.1007\/s11042-019-08348-9","volume":"79","author":"D Checa","year":"2020","unstructured":"Checa D, Bustillo A (2020) A review of immersive virtual reality serious games to enhance learning and training. Multimed Tools Appl 79(9):5501\u20135527","journal-title":"Multimed Tools Appl"},{"key":"15361_CR12","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp 785\u2013794","DOI":"10.1145\/2939672.2939785"},{"key":"15361_CR13","doi-asserted-by":"crossref","unstructured":"Fails J A, Olsen D R Jr (2003) Interactive machine learning. In: Proceedings of the 8th international conference on intelligent user interfaces, pp 39\u201345","DOI":"10.1145\/604045.604056"},{"key":"15361_CR14","doi-asserted-by":"crossref","unstructured":"Frid E, Gomes C, Jin Z (2020) Music creation by example. In: Proceedings of the 2020 CHI conference on human factors in computing systems, pp 1\u201313","DOI":"10.1145\/3313831.3376514"},{"key":"15361_CR15","unstructured":"Ghorbani A, Wexler J, Zou J Y et al (2019) Towards automatic concept-based explanations. In: Advances in neural information processing systems, p 32"},{"key":"15361_CR16","doi-asserted-by":"publisher","unstructured":"Gillies M, Fiebrink R, Tanaka A et al (2016) Human-centred machine learning. In: Proceedings of the 2016 CHI conference extended abstracts on human factors in computing systems, CHI EA \u201916. Association for Computing Machinery, New York, pp 3558\u20133565. https:\/\/doi.org\/10.1145\/2851581.2856492","DOI":"10.1145\/2851581.2856492"},{"key":"15361_CR17","unstructured":"Greydanus S, Koul A, Dodge J et al (2018) Visualizing and understanding atari agents. In: International conference on machine learning, PMLR, pp 1792\u20131801"},{"key":"15361_CR18","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"15361_CR19","doi-asserted-by":"publisher","first-page":"106,685","DOI":"10.1016\/j.knosys.2020.106685","volume":"214","author":"A Heuillet","year":"2021","unstructured":"Heuillet A, Couthouis F, D\u00edaz-Rodr\u00edguez N (2021) Explainability in deep reinforcement learning. Knowl-Based Syst 214:106,685. https:\/\/doi.org\/10.1016\/j.knosys.2020.106685. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950705120308145","journal-title":"Knowl-Based Syst"},{"key":"15361_CR20","unstructured":"Juozapaitis Z, Koul A, Fern A et al (2019) Explainable reinforcement learning via reward decomposition. In: Proceedings at the international joint conference on artificial intelligence. A workshop on explainable artificial intelligence"},{"key":"15361_CR21","unstructured":"Ke G, Meng Q, Finley T et al (2017) Lightgbm: a highly efficient gradient boosting decision tree. In: Advances in neural information processing systems, p 30"},{"key":"15361_CR22","doi-asserted-by":"crossref","unstructured":"Kuhn HW, Tucker AW (1953) Contributions to the theory of games, vol 2. Princeton University Press","DOI":"10.1515\/9781400881970"},{"key":"15361_CR23","doi-asserted-by":"crossref","unstructured":"Kulesza T, Amershi S, Caruana R et al (2014) Structured labeling for facilitating concept evolution in machine learning. In: Proceedings of the SIGCHI conference on human factors in computing systems, pp 3075\u20133084","DOI":"10.1145\/2556288.2557238"},{"key":"15361_CR24","unstructured":"Lage I, Ross A, Gershman S J et al (2018) Human-in-the-loop interpretability prior. In: Advances in neural information processing systems, p 31"},{"key":"15361_CR25","doi-asserted-by":"crossref","unstructured":"Laugwitz B, Held T, Schrepp M (2008) Construction and evaluation of a user experience questionnaire. In: Symposium of the austrian HCI and usability engineering group, springer, pp 63\u201376","DOI":"10.1007\/978-3-540-89350-9_6"},{"key":"15361_CR26","unstructured":"Lee LH, Braud T, Zhou P et al (2021) All one needs to know about metaverse: a complete survey on technological singularity, virtual ecosystem, and research agenda. arXiv:211005352"},{"key":"15361_CR27","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/j.neunet.2018.07.006","volume":"108","author":"T Lesort","year":"2018","unstructured":"Lesort T, D\u00edaz-Rodr\u00edguez N, Goudou J F et al (2018) State representation learning for control: an overview. Neural Netw 108:379\u2013392. https:\/\/doi.org\/10.1016\/j.neunet.2018.07.006. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0893608018302053","journal-title":"Neural Netw"},{"key":"15361_CR28","doi-asserted-by":"crossref","unstructured":"Louie R, Coenen A, Huang C Z et al (2020) Novice-ai music co-creation via ai-steering tools for deep generative models. In: Proceedings of the 2020 CHI conference on human factors in computing systems, pp 1\u201313","DOI":"10.1145\/3313831.3376739"},{"key":"15361_CR29","unstructured":"Lundberg S M, Lee S I (2017) A unified approach to interpreting model predictions. In: Advances in neural information processing systems, p 30"},{"key":"15361_CR30","unstructured":"Lundberg SM, Erion GG, Lee SI (2018) Consistent individualized feature attribution for tree ensembles. arXiv:180203888"},{"key":"15361_CR31","unstructured":"Lundberg SM, Erion GG, Chen H et al (2019) Explainable ai for trees: from local explanations to global understanding. CoRR arXiv:1905.04610"},{"issue":"1","key":"15361_CR32","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","volume":"2","author":"SM Lundberg","year":"2020","unstructured":"Lundberg S M, Erion G, Chen H et al (2020) From local explanations to global understanding with explainable ai for trees. Nat Mach Intell 2(1):56\u201367","journal-title":"Nat Mach Intell"},{"key":"15361_CR33","doi-asserted-by":"crossref","unstructured":"Madumal P, Miller T, Sonenberg L et al (2020) Explainable reinforcement learning through a causal lens. In: Proceedings of the AAAI conference on artificial intelligence, pp 2493\u20132500","DOI":"10.1609\/aaai.v34i03.5631"},{"key":"15361_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","volume":"267","author":"T Miller","year":"2019","unstructured":"Miller T (2019) Explanation in artificial intelligence: insights from the social sciences. Artif Intell 267:1\u201338","journal-title":"Artif Intell"},{"key":"15361_CR35","doi-asserted-by":"crossref","unstructured":"Oroojlooy A, Hajinezhad D (2022) A review of cooperative multi-agent deep reinforcement learning. Appl Intell 1\u201346","DOI":"10.1007\/s10489-022-04105-y"},{"key":"15361_CR36","doi-asserted-by":"crossref","unstructured":"Patel K, Fogarty J, Landay J A et al (2008) Investigating statistical machine learning as a tool for software development. In: Proceedings of the SIGCHI conference on human factors in computing systems, pp 667\u2013676","DOI":"10.1145\/1357054.1357160"},{"issue":"3","key":"15361_CR37","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1109\/TG.2019.2901021","volume":"11","author":"D Perez-Liebana","year":"2019","unstructured":"Perez-Liebana D, Liu J, Khalifa A et al (2019) General video game ai: a multitrack framework for evaluating agents, games, and content generation algorithms. IEEE Trans Games 11(3):195\u2013214","journal-title":"IEEE Trans Games"},{"key":"15361_CR38","unstructured":"Powers R, Shoham Y (2004) New criteria and a new algorithm for learning in multi-agent systems. In: Advances in neural information processing systems, p 17"},{"key":"15361_CR39","unstructured":"Raffin A, Hill A, Traor\u00e9 R et al (2019) Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics. In: SPIRL 2019: workshop on structure and priors in reinforcement learning at ICLR 2019"},{"issue":"5\u20136","key":"15361_CR40","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1080\/07370024.2020.1734931","volume":"35","author":"G Ramos","year":"2020","unstructured":"Ramos G, Meek C, Simard P et al (2020) Interactive machine teaching: a human-centered approach to building machine-learned models. Hum\u2013Comput Interact 35(5\u20136):413\u2013451","journal-title":"Hum\u2013Comput Interact"},{"key":"15361_CR41","doi-asserted-by":"crossref","unstructured":"Ribeiro M T, Singh S, Guestrin C (2016) \u201cWhy should i trust you?\u201d Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 1135\u20131144","DOI":"10.1145\/2939672.2939778"},{"issue":"4","key":"15361_CR42","first-page":"e1249","volume":"8","author":"O Sagi","year":"2018","unstructured":"Sagi O, Rokach L (2018) Ensemble learning: a survey. Wiley Interdiscip Rev: Data Min Knowl Discov 8(4):e1249","journal-title":"Wiley Interdiscip Rev: Data Min Knowl Discov"},{"key":"15361_CR43","unstructured":"Schapire R E (1999) A brief introduction to boosting. In: Ijcai, citeseer, pp 1401\u20131406"},{"key":"15361_CR44","doi-asserted-by":"publisher","first-page":"103367","DOI":"10.1016\/j.artint.2020.103367","volume":"288","author":"P Sequeira","year":"2020","unstructured":"Sequeira P, Gervasio M (2020) Interestingness elements for explainable reinforcement learning: Understanding agents\u2019 capabilities and limitations. Artif Intell 288:103367","journal-title":"Artif Intell"},{"key":"15361_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2020.2977026","volume":"PP","author":"W Shi","year":"2020","unstructured":"Shi W, Huang G, Song S et al (2020) Self-supervised discovering of interpretable features for reinforcement learning. IEEE Trans Pattern Anal Mach Intell PP:1\u20131. https:\/\/doi.org\/10.1109\/TPAMI.2020.3037898","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"6","key":"15361_CR46","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1080\/10447318.2020.1741118","volume":"36","author":"B Shneiderman","year":"2020","unstructured":"Shneiderman B (2020) Human-centered artificial intelligence: reliable, safe & trustworthy. Int J Hum\u2013Comput Interact 36(6):495\u2013504","journal-title":"Int J Hum\u2013Comput Interact"},{"issue":"7587","key":"15361_CR47","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison C J et al (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484\u2013489","journal-title":"Nature"},{"issue":"6419","key":"15361_CR48","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver D, Hubert T, Schrittwieser J et al (2018) A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362 (6419):1140\u20131144","journal-title":"Science"},{"key":"15361_CR49","unstructured":"Sundararajan M, Najmi A (2020) The many shapley values for model explanation. In: International conference on machine learning, PMLR, pp 9269\u20139278"},{"issue":"7782","key":"15361_CR50","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals O, Babuschkin I, Czarnecki W M et al (2019) Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575 (7782):350\u2013354","journal-title":"Nature"},{"key":"15361_CR51","doi-asserted-by":"publisher","unstructured":"Vouros GA (2022) Explainable deep reinforcement learning: state of the art and challenges. ACM Comput Surv https:\/\/doi.org\/10.1145\/3527448, just Accepted","DOI":"10.1145\/3527448"},{"key":"15361_CR52","doi-asserted-by":"publisher","unstructured":"Wiegreffe S, Pinter Y (2019) Attention is not not explanation. In: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, pp 11\u201320. https:\/\/doi.org\/10.18653\/v1\/D19-1002. https:\/\/aclanthology.org\/D19-1002","DOI":"10.18653\/v1\/D19-1002"},{"key":"15361_CR53","unstructured":"Yang G, Liu M, Hong W et al (2022) Perfectdou: dominating doudizhu with perfect information distillation. In: NeurIPS"},{"key":"15361_CR54","unstructured":"Zha D, Xie J, Ma W et al (2021) Douzero: mastering doudizhu with self-play deep reinforcement learning. In: International conference on machine learning, PMLR, pp 12333\u201312344"},{"key":"15361_CR55","unstructured":"Zhang M, Vikram S, Smith L et al (2019) Solar: deep structured representations for model-based reinforcement learning. In: International conference on machine learning, PMLR, pp 7444\u20137453"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15361-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-15361-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-15361-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T05:26:00Z","timestamp":1704518760000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-15361-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,25]]},"references-count":55,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["15361"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-15361-6","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,25]]},"assertion":[{"value":"7 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 April 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}}]}}