Non-Stationary Off-Policy Optimization

Joey Hong, Branislav Kveton, Manzil Zaheer, Yinlam Chow, Amr Ahmed
Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, PMLR 130:2494-2502, 2021.

Abstract

Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to these changes. To address this challenge, we study the novel problem of off-policy optimization in piecewise-stationary contextual bandits. Our proposed solution has two phases. In the offline learning phase, we partition logged data into categorical latent states and learn a near-optimal sub-policy for each state. In the online deployment phase, we adaptively switch between the learned sub-policies based on their performance. This approach is practical and analyzable, and we provide guarantees on both the quality of off-policy optimization and the regret during online deployment. To show the effectiveness of our approach, we compare it to state-of-the-art baselines on both synthetic and real-world datasets. Our approach outperforms methods that act only on observed context.

Cite this Paper

BibTeX
@InProceedings{pmlr-v130-hong21a, title = { Non-Stationary Off-Policy Optimization }, author = {Hong, Joey and Kveton, Branislav and Zaheer, Manzil and Chow, Yinlam and Ahmed, Amr}, booktitle = {Proceedings of The 24th International Conference on Artificial Intelligence and Statistics}, pages = {2494--2502}, year = {2021}, editor = {Banerjee, Arindam and Fukumizu, Kenji}, volume = {130}, series = {Proceedings of Machine Learning Research}, month = {13--15 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v130/hong21a/hong21a.pdf}, url = {https://proceedings.mlr.press/v130/hong21a.html}, abstract = { Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to these changes. To address this challenge, we study the novel problem of off-policy optimization in piecewise-stationary contextual bandits. Our proposed solution has two phases. In the offline learning phase, we partition logged data into categorical latent states and learn a near-optimal sub-policy for each state. In the online deployment phase, we adaptively switch between the learned sub-policies based on their performance. This approach is practical and analyzable, and we provide guarantees on both the quality of off-policy optimization and the regret during online deployment. To show the effectiveness of our approach, we compare it to state-of-the-art baselines on both synthetic and real-world datasets. Our approach outperforms methods that act only on observed context. } }
Endnote
%0 Conference Paper %T Non-Stationary Off-Policy Optimization %A Joey Hong %A Branislav Kveton %A Manzil Zaheer %A Yinlam Chow %A Amr Ahmed %B Proceedings of The 24th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2021 %E Arindam Banerjee %E Kenji Fukumizu %F pmlr-v130-hong21a %I PMLR %P 2494--2502 %U https://proceedings.mlr.press/v130/hong21a.html %V 130 %X Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to these changes. To address this challenge, we study the novel problem of off-policy optimization in piecewise-stationary contextual bandits. Our proposed solution has two phases. In the offline learning phase, we partition logged data into categorical latent states and learn a near-optimal sub-policy for each state. In the online deployment phase, we adaptively switch between the learned sub-policies based on their performance. This approach is practical and analyzable, and we provide guarantees on both the quality of off-policy optimization and the regret during online deployment. To show the effectiveness of our approach, we compare it to state-of-the-art baselines on both synthetic and real-world datasets. Our approach outperforms methods that act only on observed context.
APA
Hong, J., Kveton, B., Zaheer, M., Chow, Y. & Ahmed, A.. (2021). Non-Stationary Off-Policy Optimization . Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 130:2494-2502 Available from https://proceedings.mlr.press/v130/hong21a.html.

Related Material