Eric Pulick

Eric Pulick

5th Year PhD Student in Industrial & Systems Engineering

Posts by Collection

publications

Modeling Interaction Effects in Polarization: Individual Media Influence and the Impact of Town Meetings

Published in Journal of Artificial Societies and Social Simulation, 2016

This work uses agent-based model simulations to explore the interplay between direct, human-to-human interaction and media influence on political idea spread.

Recommended citation:

Pulick, E., Korth, P., Grim, P., & Jung, J. (2016). Modeling Interaction Effects in Polarization: Individual Media Influence and the Impact of Town Meetings. Journal of Artificial Societies and Social Simulation, 19(2), 1. DOI: 10.18564/jasss.3021

Comparing Reinforcement Learning and Human Learning with the Game of Hidden Rules

Published in IEEE Access, 2024

This work employs a novel, structured learning environment to compare differences between reinforcement learning algorithms and human learners. We propose a collection of learning tasks and show that particular elements of task structure impact human and algorithmic learners differently.

Recommended citation:

Pulick, E., Menkov, V., Mintz, Y., Kantor, P. B., & Bier, V. M. (2024). Comparing Reinforcement Learning and Human Learning with the Game of Hidden Rules. IEEE Access. DOI: 10.1109/ACCESS.2024.3395249

Idiographic Lapse Prediction with State Space Modeling: Algorithm Development and Validation

Published in Journal of Medical Internet Research - Formative Research, 2025

This paper proposes a state space framework for predicting lapse risk among individuals with alcohol use disorders. The personalized state space framework is shown to outperform population-trained classical machine learning approaches.

Recommended citation:

Pulick, E., Curtin, J., & Mintz, Y. (2025). Idiographic Lapse Prediction with State Space Modeling: Algorithm Development and Validation, Journal of Medical Internet Research - Formative Research, DOI: 10.2196/73265

An Adaptive Control Approach to Treatment Selection for Substance Use Disorders

Published in IEEE Conference on Decision and Control, 2025

This paper addresses the problem of optimally selecting treatment actions for patients with substance use disorders. Specifically, the paper introduces structured behavioral models to propose personalized learning and decision making algorithms.

Recommended citation:

Pulick, E. & Mintz, Y. (2025). An Adaptive Control Approach to Treatment Selection for Substance Use Disorders, Accepted, to appear at the 2025 IEEE Conference on Decision and Control, Preprint DOI: arXiv:2504.01221