Paper Info
Title
Off-policy Learning for Multiple Loggers
Abstract
It is well known that the historical logs are used for evaluating and learning policies in interactive systems, e.g. recommendation, search, and online advertising. Since direct online policy learning usually harms user experiences, it is more crucial to apply off-policy learning in real-world applications instead. Though there have been some existing works, most are focusing on learning with one single historical policy. However, in practice, usually a number of parallel experiments, e.g. multiple AB tests, are performed simultaneously. To make full use of such historical data, learning policies from multiple loggers becomes necessary. Motivated by this, in this paper, we investigate off-policy learning when the training data coming from multiple historical policies. Specifically, policies, e.g. neural networks, can be learned directly from multi-logger data, with counterfactual estimators. In order to understand the generalization ability of such estimator better, we conduct generalization error analysis for the empirical risk minimization problem. We then introduce the generalization error bound as the new risk function, which can be reduced to a constrained optimization problem. Finally, we give the corresponding learning algorithm for the new constrained problem, where we can appeal to the minimax problems to control the constraints. Extensive experiments on benchmark datasets demonstrate that the proposed methods achieve better performances than the state-of-the-arts.
Year
DOI
Keywords
2019
10.1145/3292500.3330864
log data, multiple loggers, off-policy learning
Field
DocType
ISSN
Data science,Computer science,Policy learning,Artificial intelligence,Machine learning
Conference
978-1-4503-6201-6
ISBN
Citations 
PageRank 
978-1-4503-6201-6
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Li He100.68
Long Xia22118.86
Wei Zeng3777.42
Zhi-Ming Ma422718.26
Yihong Zhao5181.79
Dawei Yin686661.99