{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T05:11:31Z","timestamp":1770354691893,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T00:00:00Z","timestamp":1665964800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["1829071,2106859,2119643"],"award-info":[{"award-number":["1829071,2106859,2119643"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cisco"},{"name":"NEC"},{"name":"Amazon"},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF1810208"],"award-info":[{"award-number":["W911NF1810208"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NIBIB","award":["R01-EB027650"],"award-info":[{"award-number":["R01-EB027650"]}]},{"DOI":"10.13039\/100000002","name":"NIH (National Institutes of Health)","doi-asserted-by":"publisher","award":["R35-HL135772"],"award-info":[{"award-number":["R35-HL135772"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,17]]},"DOI":"10.1145\/3511808.3557105","type":"proceedings-article","created":{"date-parts":[[2022,10,16]],"date-time":"2022-10-16T01:29:57Z","timestamp":1665883797000},"page":"3023-3032","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["<scp>ReLiable:<\/scp>Offline Reinforcement Learning for Tactical Strategies in Professional Basketball Games"],"prefix":"10.1145","author":[{"given":"Xiusi","family":"Chen","sequence":"first","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jyun-Yu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Amazon Search, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Jin","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichao","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyan","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P. Jeffrey","family":"Brantingham","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[{"name":"University of California, Los Angeles, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)0733-947X(2003)129:3(278)"},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Machine Learning. PMLR, 104--114","author":"Agarwal Rishabh","year":"2020","unstructured":"Rishabh Agarwal , Dale Schuurmans , and Mohammad Norouzi . 2020 . An optimistic perspective on offline reinforcement learning . In International Conference on Machine Learning. PMLR, 104--114 . Rishabh Agarwal, Dale Schuurmans, and Mohammad Norouzi. 2020. An optimistic perspective on offline reinforcement learning. In International Conference on Machine Learning. PMLR, 104--114."},{"key":"e_1_3_2_1_3_1","unstructured":"Raquel YS Aoki Renato M Assuncao and Pedro OS Vaz de Melo. 2017. Luck is hard to beat: The difficulty of sports prediction. In KDD. 1367--1376. Raquel YS Aoki Renato M Assuncao and Pedro OS Vaz de Melo. 2017. Luck is hard to beat: The difficulty of sports prediction. In KDD. 1367--1376."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(65)90154-X"},{"key":"e_1_3_2_1_5_1","volume-title":"Deepracer: Educational autonomous racing platform for experimentation with sim2real reinforcement learning. arXiv preprint arXiv:1911.01562","author":"Balaji Bharathan","year":"2019","unstructured":"Bharathan Balaji , Sunil Mallya , Sahika Genc , Saurabh Gupta , Leo Dirac , Vineet Khare , Gourav Roy , Tao Sun , Yunzhe Tao , Brian Townsend , 2019 . Deepracer: Educational autonomous racing platform for experimentation with sim2real reinforcement learning. arXiv preprint arXiv:1911.01562 (2019). Bharathan Balaji, Sunil Mallya, Sahika Genc, Saurabh Gupta, Leo Dirac, Vineet Khare, Gourav Roy, Tao Sun, Yunzhe Tao, Brian Townsend, et al. 2019. Deepracer: Educational autonomous racing platform for experimentation with sim2real reinforcement learning. arXiv preprint arXiv:1911.01562 (2019)."},{"key":"e_1_3_2_1_6_1","volume-title":"Science","volume":"153","author":"Bellman Richard","year":"1966","unstructured":"Richard Bellman . 1966 . Dynamic programming . Science , Vol. 153 , 3731 (1966), 34--37. Richard Bellman. 1966. Dynamic programming. Science, Vol. 153, 3731 (1966), 34--37."},{"key":"e_1_3_2_1_7_1","volume-title":"Robert Babuvs ka, and Bart De Schutter","author":"Lucian Bucs","year":"2010","unstructured":"Lucian Bucs oniu , Robert Babuvs ka, and Bart De Schutter . 2010 . Multi-agent reinforcement learning: An overview. Innovations in multi-agent systems and applications-1 (2010), 183--221. Lucian Bucs oniu, Robert Babuvs ka, and Bart De Schutter. 2010. Multi-agent reinforcement learning: An overview. Innovations in multi-agent systems and applications-1 (2010), 183--221."},{"key":"e_1_3_2_1_8_1","volume-title":"Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho , Bart Van Merri\u00ebnboer , Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014 . Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014). Kyunghyun Cho, Bart Van Merri\u00ebnboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)."},{"key":"e_1_3_2_1_9_1","volume-title":"Jan Van Haaren, and Jesse Davis","author":"Decroos Tom","year":"2019","unstructured":"Tom Decroos , Lotte Bransen , Jan Van Haaren, and Jesse Davis . 2019 . Actions speak louder than goals: Valuing player actions in soccer. In KDD. 1851--1861. Tom Decroos, Lotte Bransen, Jan Van Haaren, and Jesse Davis. 2019. Actions speak louder than goals: Valuing player actions in soccer. In KDD. 1851--1861."},{"key":"e_1_3_2_1_10_1","volume-title":"Jan Van Haaren, and Jesse Davis","author":"Decroos Tom","year":"2018","unstructured":"Tom Decroos , Jan Van Haaren, and Jesse Davis . 2018 . Automatic discovery of tactics in spatio-temporal soccer match data. In KDD. 223--232. Tom Decroos, Jan Van Haaren, and Jesse Davis. 2018. Automatic discovery of tactics in spatio-temporal soccer match data. In KDD. 223--232."},{"key":"e_1_3_2_1_11_1","volume-title":"D4rl: Datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219","author":"Fu Justin","year":"2020","unstructured":"Justin Fu , Aviral Kumar , Ofir Nachum , George Tucker , and Sergey Levine . 2020. D4rl: Datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219 ( 2020 ). Justin Fu, Aviral Kumar, Ofir Nachum, George Tucker, and Sergey Levine. 2020. D4rl: Datasets for deep data-driven reinforcement learning. arXiv preprint arXiv:2004.07219 (2020)."},{"key":"e_1_3_2_1_12_1","unstructured":"Scott Fujimoto Herke Hoof and David Meger. 2018. Addressing function approximation error in actor-critic methods. In ICML. 1587--1596. Scott Fujimoto Herke Hoof and David Meger. 2018. Addressing function approximation error in actor-critic methods. In ICML. 1587--1596."},{"key":"e_1_3_2_1_13_1","volume-title":"International conference on machine learning. PMLR","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto , David Meger , and Doina Precup . 2019 . Off-policy deep reinforcement learning without exploration . In International conference on machine learning. PMLR , 2052--2062. Scott Fujimoto, David Meger, and Doina Precup. 2019. Off-policy deep reinforcement learning without exploration. In International conference on machine learning. PMLR, 2052--2062."},{"key":"e_1_3_2_1_14_1","volume-title":"Safety-first ai for autonomous data centre cooling and industrial control. DeepMind Blog","author":"Gasparik A","year":"2018","unstructured":"A Gasparik , C Gamble , and J Gao . 2018. Safety-first ai for autonomous data centre cooling and industrial control. DeepMind Blog ( 2018 ). A Gasparik, C Gamble, and J Gao. 2018. Safety-first ai for autonomous data centre cooling and industrial control. DeepMind Blog (2018)."},{"key":"e_1_3_2_1_15_1","volume-title":"Guidelines for reinforcement learning in healthcare. Nature medicine","author":"Gottesman Omer","year":"2019","unstructured":"Omer Gottesman , Fredrik Johansson , Matthieu Komorowski , Aldo Faisal , David Sontag , Finale Doshi-Velez , and Leo Anthony Celi . 2019. Guidelines for reinforcement learning in healthcare. Nature medicine , Vol. 25 , 1 ( 2019 ), 16--18. Omer Gottesman, Fredrik Johansson, Matthieu Komorowski, Aldo Faisal, David Sontag, Finale Doshi-Velez, and Leo Anthony Celi. 2019. Guidelines for reinforcement learning in healthcare. Nature medicine, Vol. 25, 1 (2019), 16--18."},{"key":"e_1_3_2_1_16_1","volume-title":"Deep reinforcement learning for intelligent transportation systems: A survey. TITS","author":"Haydari Ammar","year":"2020","unstructured":"Ammar Haydari and Yasin Yilmaz . 2020. Deep reinforcement learning for intelligent transportation systems: A survey. TITS ( 2020 ). Ammar Haydari and Yasin Yilmaz. 2020. Deep reinforcement learning for intelligent transportation systems: A survey. TITS (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Long short-term memory. Neural computation","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber . 1997. Long short-term memory. Neural computation , Vol. 9 , 8 ( 1997 ), 1735--1780. Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation, Vol. 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_18_1","first-page":"369","article-title":"Basketball game-related statistics that discriminate between teams' season-long success","volume":"8","author":"Sergio J","year":"2008","unstructured":"Sergio J Ib\u00e1 nez, Jaime Sampaio , Sebastian Feu , Alberto Lorenzo , Miguel A G\u00f3mez , and Enrique Ortega . 2008 . Basketball game-related statistics that discriminate between teams' season-long success . EJSS , Vol. 8 , 6 (2008), 369 -- 372 . Sergio J Ib\u00e1 nez, Jaime Sampaio, Sebastian Feu, Alberto Lorenzo, Miguel A G\u00f3mez, and Enrique Ortega. 2008. Basketball game-related statistics that discriminate between teams' season-long success. EJSS, Vol. 8, 6 (2008), 369--372.","journal-title":"EJSS"},{"key":"e_1_3_2_1_19_1","volume-title":"Craig Ferguson, Agata Lapedriza, Noah Jones, Shixiang Gu, and Rosalind Picard.","author":"Jaques Natasha","year":"2019","unstructured":"Natasha Jaques , Asma Ghandeharioun , Judy Hanwen Shen , Craig Ferguson, Agata Lapedriza, Noah Jones, Shixiang Gu, and Rosalind Picard. 2019 . Way of f-policy batch deep reinforcement learning of implicit human preferences in dialog. arXiv preprint arXiv:1907.00456 (2019). Natasha Jaques, Asma Ghandeharioun, Judy Hanwen Shen, Craig Ferguson, Agata Lapedriza, Noah Jones, Shixiang Gu, and Rosalind Picard. 2019. Way off-policy batch deep reinforcement learning of implicit human preferences in dialog. arXiv preprint arXiv:1907.00456 (2019)."},{"key":"e_1_3_2_1_20_1","volume-title":"Fever Basketball: A Complex, Flexible, and Asynchronized Sports Game Environment for Multi-agent Reinforcement Learning. arXiv preprint arXiv:2012.03204","author":"Jia Hangtian","year":"2020","unstructured":"Hangtian Jia , Yujing Hu , Yingfeng Chen , Chunxu Ren , Tangjie Lv , Changjie Fan , and Chongjie Zhang . 2020 a. Fever Basketball: A Complex, Flexible, and Asynchronized Sports Game Environment for Multi-agent Reinforcement Learning. arXiv preprint arXiv:2012.03204 (2020). Hangtian Jia, Yujing Hu, Yingfeng Chen, Chunxu Ren, Tangjie Lv, Changjie Fan, and Chongjie Zhang. 2020a. Fever Basketball: A Complex, Flexible, and Asynchronized Sports Game Environment for Multi-agent Reinforcement Learning. arXiv preprint arXiv:2012.03204 (2020)."},{"key":"e_1_3_2_1_21_1","unstructured":"Hangtian Jia Chunxu Ren Yujing Hu Yingfeng Chen Tangjie Lv Changjie Fan Hongyao Tang and Jianye Hao. 2020b. Mastering basketball with deep reinforcement learning: An integrated curriculum training approach. In AAMAS. 1872--1874. Hangtian Jia Chunxu Ren Yujing Hu Yingfeng Chen Tangjie Lv Changjie Fan Hongyao Tang and Jianye Hao. 2020b. Mastering basketball with deep reinforcement learning: An integrated curriculum training approach. In AAMAS. 1872--1874."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Junqi Jin Chengru Song Han Li Kun Gai Jun Wang and Weinan Zhang. 2018. Real-time bidding with multi-agent reinforcement learning in display advertising. In CIKM. 2193--2201. Junqi Jin Chengru Song Han Li Kun Gai Jun Wang and Weinan Zhang. 2018. Real-time bidding with multi-agent reinforcement learning in display advertising. In CIKM. 2193--2201.","DOI":"10.1145\/3269206.3272021"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057023"},{"key":"e_1_3_2_1_24_1","volume-title":"Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation. arXiv preprint arXiv:1806.10293","author":"Kalashnikov Dmitry","year":"2018","unstructured":"Dmitry Kalashnikov , Alex Irpan , Peter Pastor , Julian Ibarz , Alexander Herzog , Eric Jang , Deirdre Quillen , Ethan Holly , Mrinal Kalakrishnan , Vincent Vanhoucke , 2018 a. Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation. arXiv preprint arXiv:1806.10293 (2018). Dmitry Kalashnikov, Alex Irpan, Peter Pastor, Julian Ibarz, Alexander Herzog, Eric Jang, Deirdre Quillen, Ethan Holly, Mrinal Kalakrishnan, Vincent Vanhoucke, et al. 2018a. Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation. arXiv preprint arXiv:1806.10293 (2018)."},{"key":"e_1_3_2_1_25_1","unstructured":"Dmitry Kalashnikov Alex Irpan Peter Pastor Julian Ibarz Alexander Herzog Eric Jang Deirdre Quillen Ethan Holly Mrinal Kalakrishnan Vincent Vanhoucke etal 2018b. Scalable deep reinforcement learning for vision-based robotic manipulation. In ICRL. 651--673. Dmitry Kalashnikov Alex Irpan Peter Pastor Julian Ibarz Alexander Herzog Eric Jang Deirdre Quillen Ethan Holly Mrinal Kalakrishnan Vincent Vanhoucke et al. 2018b. Scalable deep reinforcement learning for vision-based robotic manipulation. In ICRL. 651--673."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"e_1_3_2_1_27_1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky , Ilya Sutskever , and Geoffrey E Hinton . 2012 . Imagenet classification with deep convolutional neural networks . NeurIPS , Vol. 25 (2012), 1097 -- 1105 . Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. NeurIPS, Vol. 25 (2012), 1097--1105.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_28_1","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar Aviral","year":"2020","unstructured":"Aviral Kumar , Aurick Zhou , George Tucker , and Sergey Levine . 2020 . Conservative q-learning for offline reinforcement learning . Advances in Neural Information Processing Systems , Vol. 33 (2020), 1179 -- 1191 . Aviral Kumar, Aurick Zhou, George Tucker, and Sergey Levine. 2020. Conservative q-learning for offline reinforcement learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 1179--1191.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","unstructured":"Hoang Le Nan Jiang Alekh Agarwal Miroslav Dud'ik Yisong Yue and Hal Daum\u00e9. 2018. Hierarchical imitation and reinforcement learning. In ICML. Hoang Le Nan Jiang Alekh Agarwal Miroslav Dud'ik Yisong Yue and Hal Daum\u00e9. 2018. Hierarchical imitation and reinforcement learning. In ICML."},{"key":"e_1_3_2_1_30_1","unstructured":"Hoang M Le Peter Carr Yisong Yue and Patrick Lucey. 2017a. Data-driven ghosting using deep imitation learning. (2017). Hoang M Le Peter Carr Yisong Yue and Patrick Lucey. 2017a. Data-driven ghosting using deep imitation learning. (2017)."},{"key":"e_1_3_2_1_31_1","unstructured":"Hoang M Le Yisong Yue Peter Carr and Patrick Lucey. 2017b. Coordinated multi-agent imitation learning. In ICML. 1995--2003. Hoang M Le Yisong Yue Peter Carr and Patrick Lucey. 2017b. Coordinated multi-agent imitation learning. In ICML. 1995--2003."},{"key":"e_1_3_2_1_32_1","volume-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine , Aviral Kumar , George Tucker , and Justin Fu. 2020. Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 ( 2020 ). Sergey Levine, Aviral Kumar, George Tucker, and Justin Fu. 2020. Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)."},{"key":"e_1_3_2_1_33_1","first-page":"1","article-title":"Learning basketball dribbling skills using trajectory optimization and deep reinforcement learning","volume":"37","author":"Liu Libin","year":"2018","unstructured":"Libin Liu and Jessica Hodgins . 2018 . Learning basketball dribbling skills using trajectory optimization and deep reinforcement learning . TOG , Vol. 37 , 4 (2018), 1 -- 14 . Libin Liu and Jessica Hodgins. 2018. Learning basketball dribbling skills using trajectory optimization and deep reinforcement learning. TOG, Vol. 37, 4 (2018), 1--14.","journal-title":"TOG"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Yudong Luo Oliver Schulte and Pascal Poupart. 2021. Inverse reinforcement learning for team sports: valuing actions and players. In IJCAI. 3356--3363. Yudong Luo Oliver Schulte and Pascal Poupart. 2021. Inverse reinforcement learning for team sports: valuing actions and players. In IJCAI. 3356--3363.","DOI":"10.24963\/ijcai.2020\/464"},{"key":"e_1_3_2_1_35_1","volume-title":"Proc. of the MIT Sloan Sports Analytics Conference. 11--12","author":"McIntyre Avery","year":"2016","unstructured":"Avery McIntyre , Joel Brooks , John Guttag , and Jenna Wiens . 2016 . Recognizing and analyzing ball screen defense in the nba . In Proc. of the MIT Sloan Sports Analytics Conference. 11--12 . Avery McIntyre, Joel Brooks, John Guttag, and Jenna Wiens. 2016. Recognizing and analyzing ball screen defense in the nba. In Proc. of the MIT Sloan Sports Analytics Conference. 11--12."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.3390\/data4030110"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"Charbel Merhej Ryan J Beal Tim Matthews and Sarvapali Ramchurn. 2021. What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data. In KDD. 3394--3403. Charbel Merhej Ryan J Beal Tim Matthews and Sarvapali Ramchurn. 2021. What Happened Next? Using Deep Learning to Value Defensive Actions in Football Event-Data. In KDD. 3394--3403.","DOI":"10.1145\/3447548.3467090"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms1580"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.2307\/2344614"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1080\/02640414.2019.1638193"},{"key":"e_1_3_2_1_41_1","first-page":"153","article-title":"Survey of model-based reinforcement learning: Applications on robotics","volume":"86","author":"Polydoros Athanasios S","year":"2017","unstructured":"Athanasios S Polydoros and Lazaros Nalpantidis . 2017 . Survey of model-based reinforcement learning: Applications on robotics . JINT , Vol. 86 , 2 (2017), 153 -- 173 . Athanasios S Polydoros and Lazaros Nalpantidis. 2017. Survey of model-based reinforcement learning: Applications on robotics. JINT, Vol. 86, 2 (2017), 153--173.","journal-title":"JINT"},{"key":"e_1_3_2_1_42_1","volume-title":"Jan Van Haaren, and Jesse Davis","author":"Robberechts Pieter","year":"2021","unstructured":"Pieter Robberechts , Jan Van Haaren, and Jesse Davis . 2021 . A Bayesian Approach to In-Game Win Probability in Soccer. In KDD. 3512--3521. Pieter Robberechts, Jan Van Haaren, and Jesse Davis. 2021. A Bayesian Approach to In-Game Win Probability in Soccer. In KDD. 3512--3521."},{"key":"e_1_3_2_1_43_1","volume-title":"Xinyu Wei, and Patrick Lucey.","author":"Ruiz Hector","year":"2017","unstructured":"Hector Ruiz , Paul Power , Xinyu Wei, and Patrick Lucey. 2017 . \"The Leicester City Fairytale\" Utilizing New Soccer Analytics Tools to Compare Performance in the 15\/16 & 16\/17 EPL Seasons. In KDD. 1991--2000. Hector Ruiz, Paul Power, Xinyu Wei, and Patrick Lucey. 2017. \"The Leicester City Fairytale\" Utilizing New Soccer Analytics Tools to Compare Performance in the 15\/16 & 16\/17 EPL Seasons. In KDD. 1991--2000."},{"key":"e_1_3_2_1_44_1","volume-title":"Nature","volume":"550","author":"Silver David","year":"2017","unstructured":"David Silver , Julian Schrittwieser , Karen Simonyan , Ioannis Antonoglou , Aja Huang , Arthur Guez , Thomas Hubert , Lucas Baker , Matthew Lai , Adrian Bolton , 2017 . Mastering the game of go without human knowledge . Nature , Vol. 550 , 7676 (2017), 354--359. David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, et al. 2017. Mastering the game of go without human knowledge. Nature, Vol. 550, 7676 (2017), 354--359."},{"key":"e_1_3_2_1_45_1","unstructured":"Xiangyu Sun Jack Davis Oliver Schulte and Guiliang Liu. 2020. Cracking the black box: Distilling deep sports analytics. In KDD. 3154--3162. Xiangyu Sun Jack Davis Oliver Schulte and Guiliang Liu. 2020. Cracking the black box: Distilling deep sports analytics. In KDD. 3154--3162."},{"key":"e_1_3_2_1_46_1","volume-title":"Annual Review of Statistics and Its Application","volume":"8","author":"Terner Zachary","year":"2020","unstructured":"Zachary Terner and Alexander Franks . 2020 . Modeling player and team performance in basketball . Annual Review of Statistics and Its Application , Vol. 8 (2020). Zachary Terner and Alexander Franks. 2020. Modeling player and team performance in basketball. Annual Review of Statistics and Its Application, Vol. 8 (2020)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.3390\/app10010024"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12505"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_1_50_1","volume-title":"Attention is all you need. arXiv preprint arXiv:1706.03762","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , Lukasz Kaiser , and Illia Polosukhin . 2017. Attention is all you need. arXiv preprint arXiv:1706.03762 ( 2017 ). Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)."},{"key":"e_1_3_2_1_51_1","volume-title":"The advantage of doubling: A deep reinforcement learning approach to studying the double team in the NBA. arXiv preprint arXiv:1803.02940","author":"Wang Jiaxuan","year":"2018","unstructured":"Jiaxuan Wang , Ian Fox , Jonathan Skaza , Nick Linck , Satinder Singh , and Jenna Wiens . 2018. The advantage of doubling: A deep reinforcement learning approach to studying the double team in the NBA. arXiv preprint arXiv:1803.02940 ( 2018 ). Jiaxuan Wang, Ian Fox, Jonathan Skaza, Nick Linck, Satinder Singh, and Jenna Wiens. 2018. The advantage of doubling: A deep reinforcement learning approach to studying the double team in the NBA. arXiv preprint arXiv:1803.02940 (2018)."},{"key":"e_1_3_2_1_52_1","volume-title":"Proc. of MIT Sloan Sports Analytics Conference","volume":"4","author":"Wang Kuan-Chieh","year":"2016","unstructured":"Kuan-Chieh Wang and Richard Zemel . 2016 . Classifying NBA offensive plays using neural networks . In Proc. of MIT Sloan Sports Analytics Conference , Vol. 4 . Kuan-Chieh Wang and Richard Zemel. 2016. Classifying NBA offensive plays using neural networks. In Proc. of MIT Sloan Sports Analytics Conference, Vol. 4."},{"key":"e_1_3_2_1_53_1","volume-title":"Reinforcement learning in healthcare: A survey. arXiv preprint arXiv:1908.08796","author":"Yu Chao","year":"2019","unstructured":"Chao Yu , Jiming Liu , and Shamim Nemati . 2019. Reinforcement learning in healthcare: A survey. arXiv preprint arXiv:1908.08796 ( 2019 ). Chao Yu, Jiming Liu, and Shamim Nemati. 2019. Reinforcement learning in healthcare: A survey. arXiv preprint arXiv:1908.08796 (2019)."},{"key":"e_1_3_2_1_54_1","volume-title":"Xing Xie, and Zhenhui Li.","author":"Zheng Guanjie","year":"2018","unstructured":"Guanjie Zheng , Fuzheng Zhang , Zihan Zheng , Yang Xiang , Nicholas Jing Yuan , Xing Xie, and Zhenhui Li. 2018 . DRN : A deep reinforcement learning framework for news recommendation. In WWW. 167--176. Guanjie Zheng, Fuzheng Zhang, Zihan Zheng, Yang Xiang, Nicholas Jing Yuan, Xing Xie, and Zhenhui Li. 2018. DRN: A deep reinforcement learning framework for news recommendation. In WWW. 167--176."}],"event":{"name":"CIKM '22: The 31st ACM International Conference on Information and Knowledge Management","location":"Atlanta GA USA","acronym":"CIKM '22","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 31st ACM International Conference on Information &amp; Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511808.3557105","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3511808.3557105","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3511808.3557105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:56Z","timestamp":1750188656000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3511808.3557105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,17]]},"references-count":54,"alternative-id":["10.1145\/3511808.3557105","10.1145\/3511808"],"URL":"https:\/\/doi.org\/10.1145\/3511808.3557105","relation":{},"subject":[],"published":{"date-parts":[[2022,10,17]]},"assertion":[{"value":"2022-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}