This is a preview of subscription content, log in via an institution to check access.
References
Bottou L, Peters J, Quiñonero-Candela J, Charles D X, Chickering D M, Portugaly E, Ray D, Simard P, Snelson E. Counterfactual reasoning and learning systems: the example of computational advertising. Journal of Machine Learning Research, 2013, 14(1): 3207–3260
Hofmann K, Li L, Radlinski F. Online evaluation for information retrieval. Foundations and Trends in Information Retrieval, 2016, 10(1): 1–117
Li L, Chu W, Langford J, Schapire R E. A contextual-bandit approach to personalized news article recommendation. In: Proceedings of the 19th International Conference on World Wide Web. 2010, 661–670
Dudík M, Langford J, Li L. Doubly robust policy evaluation and learning. In: Proceedings of the 28th International Conference on Machine Learning. 2011, 1097–1104
Swaminathan A, Joachims T. The self-normalized estimator for counterfactual learning. In: Proceedings of the 28th International Conference on Neural Information Processing Systems. 2015, 3231–3239
Wang Y X, Agarwal A, Dudík M. Optimal and adaptive off-policy evaluation in contextual bandits. In: Proceedings of the 34th International Conference on Machine Learning. 2017, 3589–3597
Jiang N, Li L. Doubly robust off-policy evaluation for reinforcement learning. In: Proceedings of the 33rd International Conference on Machine Learning. 2016, 652–661
Li L, Munos R, Szepesvári C. Toward minimax off-policy value estimation. In: Proceedings of the 18th International Conference on Artificial Intelligence and Statistics. 2015, 608–616
Precup D, Sutton R S, Singh S P. Eligibility traces for off-policy policy evaluation. In: Proceedings of the 17th International Conference on Machine Learning. 2000, 759–766
Liu Q, Li L, Tang Z, Zhou D. Breaking the curse of horizon: infinite-horizon off-policy estimation. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2018, 5361–5371
Author information
Authors and Affiliations
Corresponding author
Additional information
Lihong Li is a research scientist at Google Brain, USA. Previously, he held research positions at Yahoo! Research (Silicon Valley) and Microsoft Research (Redmond). His main research interests are in reinforcement learning, including contextual bandits, and other related problems in AI. His work has found applications in recommendation, advertising, Web search and conversation systems, and has won best paper awards at ICML, AISTATS and WSDM. He serves as area chair or senior program committee member at major AI/ML conferences such as AAAI, ICLR, ICML, IJCAI and NIPS/NeurIPS.
Rights and permissions
About this article
Cite this article
Li, L. A perspective on off-policy evaluation in reinforcement learning. Front. Comput. Sci. 13, 911–912 (2019). https://doi.org/10.1007/s11704-019-9901-7
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11704-019-9901-7