Summary of Rebandit: Random Effects Based Online Rl Algorithm For Reducing Cannabis Use, by Susobhan Ghosh et al.
reBandit: Random Effects based Online RL algorithm for Reducing Cannabis Use
by Susobhan Ghosh, Yongyi Guo, Pei-Yao Hung, Lara Coughlin, Erin Bonar, Inbal Nahum-Shani, Maureen Walton, Susan Murphy
First submitted to arxiv on: 27 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents an online reinforcement learning algorithm called reBandit, designed to deliver personalized mobile health interventions aimed at reducing cannabis use among emerging adults (ages 18-25). reBandit utilizes random effects and Bayesian priors to learn efficiently in noisy environments. The algorithm is compared against baseline algorithms using a simulation testbed constructed from data from a prior study. Results show that reBandit performs well or better than the baselines, with a widening performance gap as population heterogeneity increases. This work has implications for addressing cannabis use and associated disorders within the 2030 United Nations Agenda for Sustainable Development Goals (SDG). The paper’s findings demonstrate the potential of reBandit in mobile health studies. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research aims to help reduce cannabis use among young adults by developing a new computer algorithm. The algorithm, called reBandit, is designed to give personalized advice and support to people who want to stop using cannabis. It uses special math techniques to learn quickly and accurately in noisy environments. To test how well it works, the researchers built a fake environment using data from previous studies and compared reBandit to other algorithms. The results show that reBandit is just as good or better than the others, especially when dealing with different groups of people. This study could help us find new ways to address cannabis use and related problems. |
Keywords
* Artificial intelligence * Reinforcement learning
