Filters








4 Hits in 1.3 sec

IntelligentPooling: Practical Thompson Sampling for mHealth [article]

Sabina Tomkins, Peng Liao, Predrag Klasnja, Susan Murphy
2020 arXiv   pre-print
To address these challenges we generalize Thompson-Sampling bandit algorithms to develop IntelligentPooling. IntelligentPooling learns personalized treatment policies thus addressing challenge one.  ...  Reinforcement learning appears ideal for learning how to optimally make these sequential treatment decisions.  ...  Furthermore, IntelligentPooling uses Thompson sampling [50] , also known as posterior sampling [45] , to select actions.  ... 
arXiv:2008.01571v2 fatcat:6afoebgld5e5jbk4q52lenzq4a

Rapidly Personalizing Mobile Health Treatment Policies with Limited Data [article]

Sabina Tomkins, Peng Liao, Predrag Klasnja, Serena Yeung, Susan Murphy
2020 arXiv   pre-print
We present IntelligentPooling, which learns personalized policies via an adaptive, principled use of other users' data.  ...  We show that IntelligentPooling achieves an average of 26% lower regret than state-of-the-art across all generative models.  ...  Our main contributions are: -INTELLIGENTPOOLING: A Thompson Sampling algorithm for rapid personalization in limited data settings.  ... 
arXiv:2002.09971v1 fatcat:njdns6sghrhmxaiwtiyxmbvfya

Guest editorial: special issue on reinforcement learning for real life

Yuxi Li, Alborz Geramifard, Lihong Li, Csaba Szepesvari, Tao Wang
2021 Machine Learning  
We received 60 submissions, following an open call for papers successfully applying RL algorithms to real-life problems and/or addressing practically relevant RL issues, with respect to practical RL algorithms  ...  , practical issues, and applications.  ...  improved sample efficiency.  ... 
doi:10.1007/s10994-021-06041-3 fatcat:ew3uhfhhevdd5khjeq2umhby7a

An Actor-Critic Contextual Bandit Algorithm for Personalized Mobile Health Interventions [article]

Huitian Lei, Yangyi Lu, Ambuj Tewari, Susan A. Murphy
2022 arXiv   pre-print
Increasing technological sophistication and widespread use of smartphones and wearable devices provide opportunities for innovative and highly personalized health interventions.  ...  Interpretability requirements in the domain of mobile health lead us to formulate the problem differently from existing formulations intended for web applications such as ad or news article placement.  ...  Intelligentpooling: Practical thompson sampling for mhealth. Machine learning, 110(9):2685-2727, 2021. Joel A Tropp. User-friendly tail bounds for sums of random matrices.  ... 
arXiv:1706.09090v2 fatcat:lqulwrcv2jccvfdl53wlglktq4