Library

A Batch, Off-Policy, Actor-Critic Algorithm for Optimizing the Average Reward

We develop an off-policy actor-critic algorithm for learning an optimal policy from a training set composed of data from multiple individuals. This algorithm is developed with a view towards its use in mobile health.

stat.MLcs.LGComputer ScienceMedicineMathematics
Source

Paper

References (27)

01Dynamic Models of Behavior for Just-in-Time Adaptive InterventionsD. Spruijt-Metz, W. Nilsen2014 · IEEE pervasive computing · 180 citations
02Development and Evaluation of a Mobile Intervention for Heavy Drinking and Smoking among College StudentsK. Witkiewitz, Sruti A. Desai, Sarah Bowen et al.2014 · Psychology of Addictive Behaviors · 128 citations
03A smartphone application to support recovery from alcoholism: A randomized controlled trialD. Gustafson, F. McTavish, Ming-Yuan Chih et al.2014 · JAMA psychiatry · 654 citations
04Mobile Health Technology EvaluationSantosh Kumar, W. Nilsen, A. Abernethy et al.2013 · American Journal of Preventive Medicine · 885 citations
05Mobile Technologies Among People with Serious Mental Illness: Opportunities for Future ServicesDror Ben-Zeev, Kristin E. Davis, Susan M. Kaiser et al.2013 · Administration and Policy in Mental Health and Mental Health Services Research · 258 citations
06Concurrent Reinforcement Learning from Customer InteractionsDavid Silver, L. Newnham, David Barker et al.2013 · International Conference on Machine Learning · 72 citations
07Harnessing Different Motivational Frames via Mobile Phones to Promote Daily Physical Activity and Reduce Sedentary Behavior in Aging AdultsA. King, E. Hekler, Lauren A. Grieco et al.2013 · PLoS ONE · 330 citations
08Computer and mobile technology-based interventions for substance use disorders: an organizing framework.Erika B. Litvin, A. Abrantes, Richard A. Brown2013 · Addictive Behaviours · 80 citations
09An Actor-Critic based controller for glucose regulation in type 1 diabetesE. Daskalaki, P. Diem, S. Mougiakakou2013 · Comput. Methods Programs Biomed. · 49 citations
10A Smartphone-Based Intervention With Diaries and Therapist-Feedback to Reduce Catastrophizing and Increase Functioning in Women With Chronic Widespread Pain: Randomized Controlled TrialÓ. Kristjansdottir, E. Fors, E. Eide et al.2013 · Journal of Medical Internet Research · 171 citations
11A Survey of Actor-Critic Reinforcement Learning: Standard and Natural Policy GradientsI. Grondman, L. Buşoniu, G. D. Lopes et al.2012 · IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews) · 1.0k citations
12Intelligent real-time therapy: Harnessing the power of machine learning to optimise the delivery of momentary cognitive–behavioural interventionsJames Kelly, P. Gooding, Daniel Pratt et al.2012 · Journal of Mental Health · 75 citations

Scroll for more · 15 remaining

Similar papers

Off-Policy Average Reward Actor-Critic with Deterministic Policy SearchNaman Saxena, Subhojyoti Khastigir, Shishir Kolathaya et al.2023 · NOT FOUND REPOSITORY (Indian Institute of Science Bangalore) · 14 citations In Library
Batch Policy Learning in Average Reward Markov Decision ProcessesPeng Liao, Zhengling Qi, Runzhe Wan et al.2020 · Annals of Statistics · 98 citations In Library
Off-Policy Actor-CriticT. Degris, Martha White, R. Sutton2012 · International Conference on Machine Learning · 213 citations In Library
Average-Reward Soft Actor-CriticJacob Adamczyk, Volodymyr Makarenko, Stas Tiomkin et al.2025 · 10 citations In Library
Variance-Constrained Actor-Critic Algorithms for Discounted and Average Reward MDPsPrashanth L.A., M. Ghavamzadeh2014 · Machine-mediated learning · 76 citations In Library
Optimal Actor-Critic Policy With Optimized Training DatasetsChayan Banerjee, Zhiyong Chen, Nasimul Noman et al.2022 · IEEE Transactions on Emerging Topics in Computational Intelligence In Library
A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic ApproachSwetha Ganesh, Washim Uddin Mondal, Vaneet Aggarwal2024 · International Conference on Machine Learning · 15 citations In Library
Optimal Actor-Critic Policy with Optimized Training DatasetsC. Banerjee, Zhiyong Chen, N. Noman et al.2021 · IEEE Transactions on Emerging Topics in Computational Intelligence · 10 citations In Library
Hierarchical Average Reward Policy Gradient AlgorithmsAkshay Dharmavaram, M. Riemer, S. Bhatnagar2019 · AAAI Conference on Artificial Intelligence · 0 citations In Library
Sample-Efficient Model-Free Reinforcement Learning with Off-Policy CriticsDenis Steckelmacher, Hélène Plisnier, D. Roijers et al.2019 · BNAIC/BENELEARN · 18 citations In Library
© 2026 NYSGPT2525 LLC