Scholar
Susobhan Ghosh
Google Scholar ID: 3NhEFSAAAAAJ
Harvard University
Citations & Impact
Citations
126
H-index
7
i10-index
5
Publications
18
Co-authors
23
list available
Publications
Resume (English only)
Academic Achievements
- Published 'Reproducible workflow for online AI in digital health' in Philosophical Transactions of The Royal Society A
- Paper on MiWaves JITAI user experience accepted at EAI Pervasive Health 2025
- ‘ReBandit: Random Effects Based Online RL Algorithm for Reducing Cannabis Use’ accepted at IJCAI 2024
- ‘Did we personalize? assessing personalization by an online reinforcement learning algorithm using resampling’ published in Machine Learning Journal
- Co-authored ‘VidyutVanika: AI-Based Autonomous Broker for Smart Grids’ in Power TAC proceedings
- ‘Fairness for Workers Who Pull the Arms’ accepted at AAMAS 2023
- Contributed to ArchGym, an open-source platform for ML-assisted architecture design (ISCA 2023)
- Two papers accepted at AAAI 2022: on mobile health clinic demand prediction and human-wildlife cohabitation
Research Experience
- Conducting research on Bayesian RL for mobile health interventions in the StatRL group at Harvard
- Developed and deployed the reBandit algorithm in the MiWaves clinical trial
- Contributing to the JITAI-Twins framework for optimizing Just-in-Time Adaptive Interventions
- Working on effective monitoring of online decision-making algorithms in digital health implementation
- Previously involved in interdisciplinary projects on computational sustainability, smart grids, human-wildlife conflict prediction, and mobile health clinic demand forecasting
Background
- Sixth-year (final year) CS PhD student in the StatRL research group at Harvard University
- Advised by Prof. Susan Murphy
- Currently focusing on designing Bayesian Reinforcement Learning algorithms for Mobile Health interventions through clinical trials
- Recently developed and deployed the reBandit algorithm for the MiWaves clinical trial (Mar–May 2024) to reduce cannabis use among emerging adults (ages 18–25)
- Past work spans Multi-Agent Systems, Game Theory & Mechanism Design, and Machine Learning
- Has applied these methods to mobile health, computational sustainability, social problems (e.g., security and planning), and adversarial settings
