Rupali Bhati
PHD Student at Northeastern University
Boston, Massachusetts, United States
Summary
👤
Senior🎓
Top SchoolRupali Bhati is a PhD student and independent reinforcement learning researcher based in Boston with eight years of experience applying RL across healthcare, energy, finance, and multi-agent settings. Her work spans academic research at Northeastern, Université Laval and Mila, plus industry impact—using DQN to boost HVAC efficiency by over 70% and developing risk-averse CARL framed as a Stackelberg game. She teaches and mentors regularly, translating complex RL concepts into workshops and courses for students and professionals. Projects include disentangling non-stationarity in multi-agent games like Diplomacy and interpretable clinical models using GBDTs with SHAP, revealing a blend of theoretical depth and practical interpretability. Colleagues describe her as a researcher who pairs rigorous theory with hands-on solutions that drive measurable operational gains.
8 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy - PhD, Doctor of Philosophy - PhD at Northeastern UniversityMaster's in Science, Computer Science, Master's in Science, Computer Science at Université LavalBachelor of Technology (B.Tech.), Electronics and Communication, Bachelor of Technology (B.Tech.), Electronics and Communication at Delhi Technological University(formerly Delhi College of Engineering)British International School, BratislavaLe Bocage International School, Mauritius
English, French, Hindi
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (15)
perceptron8
simulation8
algorithm7
fibonacci6
reinforcement-learning5
machine-learning4
multi-agent-reinforcement-learning4
deep-learning3
artificial-intelligence3
python3
pytorch3
computer-vision3
image-processing3
rlhf2
ai2
Programming languages (4)
Github contributions (5)
RupaliBhati/rupalibhati.github.io
Dec 2018 - May 2026
Portfolio
Contributions:154 pushes, 1 branch in 7 years 6 months
cssjavascriptreact
RupaliBhati/Traffic-Light-Control-using-Reinforcement-Learning
Jun 2019 - Jun 2019
Traffic Light Control problem using Actor- Critic algorithm in Simulation of Urban Mobility (SUMO) simulator
Contributions:10 commits, 8 pushes, 1 branch in 1 day
simulation
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.