Reinforcement learning (RL) is a subfield of machine learning concerned with sequential decision making under uncertainty. In the past decade, RL has seen breakthroughs in game domains (such as AlphaGOandAlphaStar). However, applying RL to realworld applications is still challenging due to the requirementof online interaction and its susceptibility to distribution shift. Imagine trusting a health diagnosis toa system that might not be accurate if the microscope lenses are different from those used during training, or some other factor that causes the distribution of outcomes to shift. 

In this team, students will investigate core RL methods that would enable realworld applications. Students will apply reinforcement learning to solve sequential decision making and combinatorial optimization problems encountered in healthcare and physical science problems, such as patient treatment recommendations using Electronic Health Records, molecular designs, and physical device designs.

Topics include modelbased RL, offline RL, meta RL, and multiobjective RL. Also, we will develop reinforcement learning methods for healthcare and physical science applications.

Meeting time and location:

For academic credit, our MDP course is classified as a hybrid course but will mainly meet remotely, following university public health informed guidelines. Our team typically meets on Friday 3:30 pm 5:30 pm ET virtually. A best time will be finalized once students are identified. Each subteam arranges a convenient time to meet and work together. A twoterm commitment will begin January 2021.

Team organization:

Each subteam has a team leader that reports to and meets with the faculty PI. The teams are flexibly structured to enhance creativity and opportunity for student growth.

More information

First-year undergraduates through masters graduate students are welcome to apply, and all will be encouraged to stay on the team for more than the two-semester minimum. Leadership roles are available in the lab, and experienced students will be a natural fit for these positions as their knowledge grows over time.

Core Reinforcement Learning Analysis (3 – 4 Students)

Preferred Skills: Reinforcement learning, machine learning, deep learning, Python

Likely Majors: Biostats, CSE/CSLSA, CE, EE, DATA, IOE, STATS

Healthcare Reinforcement Learning Analysts (3 Students)

Preferred Skills: Statistics, reinforcement learning, machine learning, python

Likely Majors: Biostats, CSE/CSLSA, CE, EE, DATA, HEALTH INFORMATICS, IOE, SI, Stats

Physical Science Reinforcement Learning Analysts (3 Students)

Preferred Skills: Reinforcement learning, machine learning, deep learning, physics/chemistry/optics, Python


Apprentice Researchers (3 Students)

Preferred Skills: Interest in project material, willingness to develop skills. Open to first-year and second-year undergraduate students ONLY. 

Likely Majors: ANY

Faculty Sponsor

Jay Guo
Professor, Electrical Engineering and Computer Science Professor (courtesy), Mechanical Engineering; Applied Physics; Macromolecular Science & Engineering L. Jay Guois a Professor of Electrical Engineering and Computer Science, with joint appointment in Applied Physics, Mechanical Engineering, Macromolecular Science and Engineering. His group’s researches include polymer-based photonic devices and sensor applications, organic and hybrid photovoltaicsand photodetectors, plasmonic nanophotonicsand structural colors, nanoimprint-based,roll to roll nanomanufacturing technologies, and machine learning for physical science applications.

Students: ~ 9 Students


Summer Opportunity: Summer research fellowships may be available for qualifying students.

Citizenship Requirements: This project is open to all students on campus.

IP: Students who successfully match to this project team will be required to sign an Intellectual Property (IP) Agreement and complete PEERRS and Health Insurance Portability and Accountability Act (HIPAA) training prior and a non-disclosure agreement prior to participation in January 2021.

Course Substitutions: Honors