Nirbhay Modhe

Nirbhay Modhe

Post-Doctoral Fellow

Emory University

Biography

I am a Post-Doctoral Fellow at the Center for Data Science in the Nell Hodgson Woodruff School of Nursing at Emory University, working with Prof. Xiao Hu. Prior to this, I have received my PhD in Computer Science from the School of Interactive Computing within the College of Computing at Georgia Tech, where I was advised by Prof. Dhruv Batra. I have received my bachelor’s degree in Computer Science from IIT Kanpur, where I worked with Prof. Piyush Rai.

My long term goal is to develop machine learning and reinforcement learning algorithms for biomedical data analysis and sequential decision making in medical treatment.

I also enjoy powerlifting, hiking, and speed solving. My official World Cube Association record for fastest single solve of the 3 x 3 Rubik’s Cube is 15.33 seconds.

Interests
  • Reinforcement Learning
  • Machine Learning
  • Biomedical and Health Applications
Education

  • Doctor of Philosophy in Computer Science, 2017-2022

    Georgia Tech

  • Bachelor of Technology in Computer Science, 2017

    Indian Institute of Technology Kanpur

Featured Articles

Nirbhay Modhe, Ran Xiao, Matthew Clark, Cheng Ding, Duc Do, Randall Lee, Timothy Ruchti, Xiao Hu
June, 2023 Accepted as Extended Abstract In IEEE BHI 2023
Time-Aware Deep Sequential Models for In-Hospital Code Blue Prediction using Monitor Alarms
Time-Aware Deep Sequential Models for In-Hospital Code Blue Prediction using Monitor Alarms
Cite
Nirbhay Modhe, Qiaozi Gao, Dhruv Batra, Ashwin Kalyan, Govind Thattai, Gaurav Sukhatme
September, 2022
Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations
Exploiting Generalization in Offline Reinforcement Learning via Unseen State Augmentations
PDF Cite ArXiv
Nirbhay Modhe, Harish Kamath, Dhruv Batra, Ashwin Kalyan
August, 2021
Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice
Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice
PDF Cite Code ArXiv
Nirbhay Modhe, Harish Kamath, Dhruv Batra, Ashwin Kalyan
June, 2020 In 4th Lifelong Machine Learning Workshop at ICML 2020
Bridging Worlds in Reinforcement Learning with Model-Advantage
Bridging Worlds in Reinforcement Learning with Model-Advantage
PDF Cite
Nirbhay Modhe, Prithvijit Chattopadhyay, Mohit Sharma, Abhishek Das, Devi Parikh, Dhruv Batra
April, 2020 In IJCAI 2020
IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL
IR-VIC: Unsupervised Discovery of Sub-goals for Transfer in RL
PDF Cite IJCAI ArXiv
See all publications

Teaching

Lectures

  • Georgia Tech, Fall 2020, OMSCS CS7643: Deep Learning, Fall 2020, by Prof. Zsolt Kira. Four lectures for the Reinforcement Learning module. Recorded lecture videos available as a part of the OMSCS course offering.

  • Georgia Tech, Fall 2020, CS4803 / CS7643: Deep Learning, Fall 2020, by Prof. Dhruv Batra. Three lectures for the Reinforcement Learning module. Lecture slides: 1, 2, 3.

  • Georgia Tech, Fall 2019, CS4803 / CS7643: Deep Learning, Fall 2019. Lecture on Reinforcement Learning - Dynamic Programming, Q-Learning DQNs. Slides.

  • IIT Kanpur, Spring 2017, ESC101: Fundamentals of Computer Science.

    • Recorded lecture videos in Hindi (partly mixed with English) jointly with all tutors in order to help students who had difficulty understanding English lectures. Sample: Video 1 - Multidimensional Arrays. All lecture videos available at this YouTube Playlist.

Teaching Assistant

  • Georgia Tech, Fall 2019, CS4803 / CS7643: Deep Learning, by Prof. Dhruv Batra

  • Georgia Tech, Fall 2018, CS4803 / CS7643: Deep Learning, by Prof. Dhruv Batra


Tutor: Held weekly tutorial classes (read: recitations) along with holding TAing duties for:

Contact

  • nmodhe [AT] emory [DOT] edu
  • Atlanta, GA