Abstract
This paper considers the actor-critic contextual bandit for the mobile health (mHealth) intervention. The state-of-the-art decision-making methods in the mHealth generally assume that the noise in the dynamic system follows the Gaussian distribution. Those methods use the least-square-based algorithm to estimate the expected reward, which is prone to the existence of outliers. To deal with the issue of outliers, we are the first to propose a novel robust actor-critic contextual bandit method for the mHealth intervention. In the critic updating, the capped-\(\ell _{2}\) norm is used to measure the approximation error, which prevents outliers from dominating our objective. A set of weights could be achieved from the critic updating. Considering them gives a weighted objective for the actor updating. It provides the ineffective sample in the critic updating with zero weights for the actor updating. As a result, the robustness of both actor-critic updating is enhanced. There is a key parameter in the capped-\(\ell _{2}\) norm. We provide a reliable method to properly set it by making use of one of the most fundamental definitions of outliers in statistics. Extensive experiment results demonstrate that our method can achieve almost identical results compared with the state-of-the-art methods on the dataset without outliers and dramatically outperform them on the datasets noised by outliers.
This work was partially supported by NSF IIS-1423056, CMMI-1434401, CNS-1405985, IIS-1718853 and the NSF CAREER grant IIS-1553687.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Dudík, M., Langford, J., Li, L.: Doubly robust policy evaluation and learning. In: ICML, pp. 1097–1104 (2011)
Gao, H., Nie, F., Cai, T.W., Huang, H.: Robust capped norm nonnegative matrix factorization: capped norm NMF. In: ACM International Conference on Information and Knowledge, pp. 871–880 (2015)
Grondman, I., Busoniu, L., Lopes, G.A.D., Babuska, R.: A survey of actor-critic reinforcement learning: standard and natural policy gradients. IEEE Trans. Syst. Man Cybern. 42(6), 1291–1307 (2012)
Lei, H.: An online actor critic algorithm and a statistical decision procedure for personalizing intervention. Ph.D. thesis, University of Michigan (2016)
Lei, H., Tewari, A., Murphy, S.: An actor-critic contextual bandit algorithm for personalized interventions using mobile devices. In: NIPS 2014 Workshop: Personalization: Methods and Applications, pp. 1–9 (2014)
Li, L., Chu, W., Langford, J., Schapire, R.E.: A contextual-bandit approach to personalized news article recommendation. In: International Conference on World Wide Web (WWW), pp. 661–670 (2010)
Liao, P., Tewari, A., Murphy, S.: Constructing just-in-time adaptive interventions. Ph.D. Section Proposal, pp. 1–49 (2015)
Murphy, S.A., Deng, Y., Laber, E.B., Maei, H.R., Sutton, R.S., Witkiewitz, K., et al.: A batch, off-policy, actor-critic algorithm for optimizing the average reward. CoRR abs/ arXiv:1607.05047 (2016)
Nie, F., Wang, H., Cai, X., Huang, H., Ding, C.: Robust matrix completion via joint schatten p-norm and lp-norm minimization. In: IEEE International Conference on Data Mining (ICDM), pp. 566–574. Washington, DC, USA (2012)
Sun, Q., Xiang, S., Ye, Y.: Robust principal component analysis via capped norms. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 311–319 (2013)
Tewari, A., Murphy, S.A.: From ads to interventions: contextual bandits in mobile health. In: Rehg, J., Murphy, S.A., Kumar, S. (eds.) Mobile Health: Sensors, Analytic Methods, and Applications. Springer, Berlin (2017)
Zhou, L., Brunskill, E.: Latent contextual bandits and their application to personalized recommendations for new users. In: International Joint Conference on Artificial Intelligence, pp. 3646–3653 (2016)
Zhu, F., Fan, B., Zhu, X., Wang, Y., Xiang, S., Pan, C., et al.: 10,000\(+\) times accelerated robust subset selection (ARSS). Proc. Assoc. Adv. Artif. Intell. (AAAI). 3217–3224 (2015). http://arxiv.org/abs/1409.3660
Zhu, F., Wang, Y., Fan, B., Meng, G., Pan, C.: Effective spectral unmixing via robust representation and learning-based sparsity. CoRR abs/1409.0685 (2014). http://arxiv.org/abs/1409.0685
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix: The Proof of Proposition 1
Appendix: The Proof of Proposition 1
Proof
The objective of (3) is non-convex and non-differentiable [2, 10]. We could obtain its sub-gradient: \(\partial O\left( \mathbf {w}\right) =\sum _{i}\partial \min \left\{ \left\| r_{i}-\mathbf {x}_{i}^{T}\mathbf {w}\right\| _{2}^{2},\epsilon \right\} +2\zeta \mathbf {w},\) where
Letting \(u_{i}=1_{\left\{ \left\| r_{i}-\mathbf {x}_{i}^{T} \mathbf {w}\right\| _{2}^{2}<\epsilon \right\} }\) for \(i\in \left\{ 1,\cdots ,T\right\} \) gives a simplified partial derivative of (3) that satisfies the sub-gradient (10). It is defined as
which is equivalent to the partial derivative of the following objective
From the perspective of optimization, the objective (11) is equivalent to (3). \(\square \)
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, F., Zhu, X., Wang, S., Yao, J., Xiao, Z., Huang, J. (2018). Robust Contextual Bandit via the Capped-\(\ell _{2}\) Norm for Mobile Health Intervention. In: Shi, Y., Suk, HI., Liu, M. (eds) Machine Learning in Medical Imaging. MLMI 2018. Lecture Notes in Computer Science(), vol 11046. Springer, Cham. https://doi.org/10.1007/978-3-030-00919-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-00919-9_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00918-2
Online ISBN: 978-3-030-00919-9
eBook Packages: Computer ScienceComputer Science (R0)