{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T17:58:16Z","timestamp":1764784696922,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":59,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462813","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T03:08:25Z","timestamp":1626059305000},"page":"2669-2672","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Reinforcement Learning for Information Retrieval"],"prefix":"10.1145","author":[{"given":"Alexander","family":"Kuhnle","sequence":"first","affiliation":[{"name":"Blue Prism AI Labs, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miguel","family":"Aroca-Ouellette","sequence":"additional","affiliation":[{"name":"Blue Prism AI Labs, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anindya","family":"Basu","sequence":"additional","affiliation":[{"name":"Blue Prism AI Labs, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Murat","family":"Sensoy","sequence":"additional","affiliation":[{"name":"Blue Prism AI Labs, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Reid","sequence":"additional","affiliation":[{"name":"Blue Prism AI Labs, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dell","family":"Zhang","sequence":"additional","affiliation":[{"name":"Blue Prism AI Labs, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3411547"},{"key":"e_1_3_2_1_2_1","volume-title":"Exploration by Random Network Distillation. arXiv:1810.12894 [cs, stat] (Oct","author":"Burda Yuri","year":"2018","unstructured":"Yuri Burda, Harrison Edwards, Amos Storkey, and Oleg Klimov. 2018. Exploration by Random Network Distillation. arXiv:1810.12894 [cs, stat] (Oct. 2018). arxiv: 1810.12894 [cs, stat]"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3289600.3290999"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449846"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2018396.2018423"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3121050.3121108"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1561\/1500000067"},{"volume-title":"Deep Learning","author":"Goodfellow Ian","key":"e_1_3_2_1_8_1","unstructured":"Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning .MIT Press ."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1207631"},{"key":"e_1_3_2_1_10_1","volume-title":"Dream to Control : Learning Behaviors by Latent Imagination. arXiv:1912.01603 [cs] (March","author":"Hafner Danijar","year":"2020","unstructured":"Danijar Hafner, Timothy Lillicrap, Jimmy Ba, and Mohammad Norouzi. 2020. Dream to Control : Learning Behaviors by Latent Imagination. arXiv:1912.01603 [cs] (March 2020). arxiv: 1912.01603 [cs]"},{"key":"e_1_3_2_1_11_1","volume-title":"Rainbow: Combining Improvements in Deep Reinforcement Learning. In Thirty-Second AAAI Conference on Artificial Intelligence .","author":"Hessel Matteo","year":"2018","unstructured":"Matteo Hessel, Joseph Modayil, Hado Van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horgan, Bilal Piot, Mohammad Azar, and David Silver. 2018. Rainbow: Combining Improvements in Deep Reinforcement Learning. In Thirty-Second AAAI Conference on Artificial Intelligence ."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--72113--8"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030--72240--1"},{"key":"e_1_3_2_1_14_1","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Ho Jonathan","year":"2016","unstructured":"Jonathan Ho and Stefano Ermon. 2016. Generative Adversarial Imitation Learning. Advances in Neural Information Processing Systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_15_1","volume-title":"Reinforcement Learning for Slate -Based Recommender Systems : A Tractable Decomposition and Practical Methodology. arXiv:1905.12767 [cs, stat] (May","author":"Ie Eugene","year":"2019","unstructured":"Eugene Ie, Vihan Jain, Jing Wang, Sanmit Narvekar, Ritesh Agarwal, Rui Wu, Heng-Tze Cheng, Morgane Lustman, Vince Gatto, Paul Covington, Jim McFadden, Tushar Chandra, and Craig Boutilier. 2019. Reinforcement Learning for Slate -Based Recommender Systems : A Tractable Decomposition and Practical Methodology. arXiv:1905.12767 [cs, stat] (May 2019). arxiv: 1905.12767 [cs, stat]"},{"key":"e_1_3_2_1_16_1","first-page":"21810","article-title":"MOReL : Model -Based Offline Reinforcement Learning","volume":"33","author":"Kidambi Rahul","year":"2020","unstructured":"Rahul Kidambi, Aravind Rajeswaran, Praneeth Netrapalli, and Thorsten Joachims. 2020. MOReL : Model -Based Offline Reinforcement Learning. Advances in Neural Information Processing Systems, Vol. 33 (2020), 21810--21823.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_17_1","volume-title":"Advances in Neural Information Processing Systems","volume":"12","author":"Konda Vijay","year":"1999","unstructured":"Vijay Konda and John Tsitsiklis. 1999. Actor-Critic Algorithms. Advances in Neural Information Processing Systems, Vol. 12 (1999)."},{"volume-title":"Bandit Algorithms","author":"Lattimore Tor","key":"e_1_3_2_1_18_1","unstructured":"Tor Lattimore and Csaba Szepesv\u00e1ri. 2020. Bandit Algorithms .Cambridge University Press ."},{"key":"e_1_3_2_1_19_1","volume-title":"Nature","volume":"521","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep Learning. Nature, Vol. 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_1_20_1","volume-title":"Offline Reinforcement Learning : Tutorial, Review, and Perspectives on Open Problems. arXiv:2005.01643 [cs, stat] (Nov","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:2005.01643 [cs, stat] (Nov. 2020). arxiv: 2005.01643 [cs, stat]"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914800"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380130"},{"key":"e_1_3_2_1_23_1","volume-title":"Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu.","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adri\u00e0 Puigdom\u00e8nech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. arXiv:1602.01783 [cs] (Feb. 2016). arxiv: 1602.01783 [cs]"},{"key":"e_1_3_2_1_24_1","volume-title":"Nature","volume":"518","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, and Georg Ostrovski. 2015. Human-Level Control through Deep Reinforcement Learning. Nature, Vol. 518, 7540 (2015), 529."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401099"},{"key":"e_1_3_2_1_26_1","volume-title":"Vedavyas Panneershelvam, Mustafa Suleyman, Charles Beattie, Stig Petersen, Shane Legg, Volodymyr Mnih, Koray Kavukcuoglu, and David Silver.","author":"Nair Arun","year":"2015","unstructured":"Arun Nair, Praveen Srinivasan, Sam Blackwell, Cagdas Alcicek, Rory Fearon, Alessandro De Maria, Vedavyas Panneershelvam, Mustafa Suleyman, Charles Beattie, Stig Petersen, Shane Legg, Volodymyr Mnih, Koray Kavukcuoglu, and David Silver. 2015. Massively Parallel Methods for Deep Reinforcement Learning. arXiv:1507.04296 [cs] (July 2015). arxiv: 1507.04296 [cs]"},{"key":"e_1_3_2_1_27_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Nasiriany Soroush","year":"2019","unstructured":"Soroush Nasiriany, Vitchyr Pong, Steven Lin, and Sergey Levine. 2019. Planning with Goal -Conditioned Policies. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_28_1","first-page":"2","article-title":"Algorithms for Inverse Reinforcement Learning","volume":"1","author":"Ng Andrew Y.","year":"2000","unstructured":"Andrew Y. Ng and Stuart J. Russell. 2000. Algorithms for Inverse Reinforcement Learning.. In ICML, Vol. 1. 2.","journal-title":"ICML"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"e_1_3_2_1_31_1","volume-title":"Neural Episodic Control. arXiv:1703.01988 [cs, stat] (March","author":"Pritzel Alexander","year":"2017","unstructured":"Alexander Pritzel, Benigno Uria, Sriram Srinivasan, Adri\u00e0 Puigdom\u00e8nech, Oriol Vinyals, Demis Hassabis, Daan Wierstra, and Charles Blundell. 2017. Neural Episodic Control. arXiv:1703.01988 [cs, stat] (March 2017). arxiv: 1703.01988 [cs, stat]"},{"key":"e_1_3_2_1_32_1","volume-title":"Relational Recurrent Neural Networks. arXiv:1806.01822 [cs, stat] (June","author":"Santoro Adam","year":"2018","unstructured":"Adam Santoro, Ryan Faulkner, David Raposo, Jack Rae, Mike Chrzanowski, Theophane Weber, Daan Wierstra, Oriol Vinyals, Razvan Pascanu, and Timothy Lillicrap. 2018. Relational Recurrent Neural Networks. arXiv:1806.01822 [cs, stat] (June 2018). arxiv: 1806.01822 [cs, stat]"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2010167"},{"key":"e_1_3_2_1_34_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, and Marc Lanctot.","author":"Silver David","year":"2016","unstructured":"David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, and Marc Lanctot. 2016. Mastering the Game of Go with Deep Neural Networks and Tree Search. Nature, Vol. 529, 7587 (2016), 484--489."},{"key":"e_1_3_2_1_35_1","volume-title":"Deterministic Policy Gradient Algorithms. In International Conference on Machine Learning. PMLR, 387--395","author":"Silver David","year":"2014","unstructured":"David Silver, Guy Lever, Nicolas Heess, Thomas Degris, Daan Wierstra, and Martin Riedmiller. 2014. Deterministic Policy Gradient Algorithms. In International Conference on Machine Learning. PMLR, 387--395."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000068"},{"key":"e_1_3_2_1_37_1","volume-title":"Barto","author":"Sutton Richard S.","year":"2018","unstructured":"Richard S. Sutton and Andrew G. Barto. 2018. Reinforcement Learning : An Introduction second ed.). MIT Press ."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080786"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_40_1","volume-title":"Machine learning","author":"Watkins Christopher JCH","year":"1992","unstructured":"Christopher JCH Watkins and Peter Dayan. 1992. Q-Learning. Machine learning, Vol. 8, 3--4 (1992), 279--292."},{"key":"e_1_3_2_1_41_1","unstructured":"Christopher John Cornish Hellaby Watkins. 1989. Learning from Delayed Rewards. (1989)."},{"key":"e_1_3_2_1_42_1","volume-title":"Unsupervised Predictive Memory in a Goal -Directed Agent. arXiv:1803.10760 [cs, stat] (March","author":"Wayne Greg","year":"2018","unstructured":"Greg Wayne, Chia-Chun Hung, David Amos, Mehdi Mirza, Arun Ahuja, Agnieszka Grabska-Barwinska, Jack Rae, Piotr Mirowski, Joel Z. Leibo, Adam Santoro, Mevlana Gemici, Malcolm Reynolds, Tim Harley, Josh Abramson, Shakir Mohamed, Danilo Rezende, David Saxton, Adam Cain, Chloe Hillier, David Silver, Koray Kavukcuoglu, Matt Botvinick, Demis Hassabis, and Timothy Lillicrap. 2018. Unsupervised Predictive Memory in a Goal -Directed Agent. arXiv:1803.10760 [cs, stat] (March 2018). arxiv: 1803.10760 [cs, stat]"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080685"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080775"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16579"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401147"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401148"},{"key":"e_1_3_2_1_49_1","volume-title":"Offline Pretraining for Sequential Decision Making. arXiv:2102.05815 [cs] (Feb","author":"Yang Mengjiao","year":"2021","unstructured":"Mengjiao Yang and Ofir Nachum. 2021. Representation Matters : Offline Pretraining for Sequential Decision Making. arXiv:2102.05815 [cs] (Feb. 2021). arxiv: 2102.05815 [cs]"},{"key":"e_1_3_2_1_50_1","volume-title":"An Overview of Multi -Agent Reinforcement Learning from Game Theoretical Perspective. arXiv:2011.00583 [cs] (March","author":"Yang Yaodong","year":"2021","unstructured":"Yaodong Yang and Jun Wang. 2021. An Overview of Multi -Agent Reinforcement Learning from Game Theoretical Perspective. arXiv:2011.00583 [cs] (March 2021). arxiv: 2011.00583 [cs]"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3234944.3234977"},{"key":"e_1_3_2_1_52_1","first-page":"97","article-title":"Imitation Learning to Rank","volume":"34","author":"Zeng Wei","year":"2020","unstructured":"Wei Zeng, Weiijie Yu, Jun Xu, Lan, Yanyan, and Cheng, Xueqi. 2020. Imitation Learning to Rank. Journal of Chinese Information Processing, Vol. 34, 1 (2020), 97--105.","journal-title":"Journal of Chinese Information Processing"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401467"},{"key":"e_1_3_2_1_54_1","volume-title":"Deep Reinforcement Learning for Online Advertising in Recommender Systems. arXiv:1909.03602 [cs] (Sept","author":"Zhao Xiangyu","year":"2019","unstructured":"Xiangyu Zhao, Changsheng Gu, Haoshenglun Zhang, Xiaobing Liu, Xiwang Yang, and Jiliang Tang. 2019. Deep Reinforcement Learning for Online Advertising in Recommender Systems. arXiv:1909.03602 [cs] (Sept. 2019). arxiv: 1909.03602 [cs]"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403384"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3356464.3357707"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371801"}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Virtual Event Canada","acronym":"SIGIR '21"},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462813","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462813","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:16Z","timestamp":1750193236000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462813"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":59,"alternative-id":["10.1145\/3404835.3462813","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462813","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}