I am a Ph.D. student in Computer Science at McGill University working with Dr. Doina Precup at Mila and Reasoning and learning lab (rllab). My research focus is on “Improving the Capacity of Neural Networks for Reinforcement Learning Agents”. I am working on efficiently using neural networks where we take inspiration from the human brain, using multiple specialized pathways through a single network, with each pathway focusing on a single task. This is an alternate way to “routing” and a mixture of expert structures that can be added to LLM. I’m also interested in General Value functions, Multitask Learning, Sequential RL using auto-regressive model (ex: transformer), Representation learning for better generalization and exploration, and Hierarchical Learning.

I completed Master’s in Electrical and Computer Engineering at McGill University. My master’s research was on “Adversarial Inverse Reinforcement Learning” under the supervision of Dr. Aditya Mahajan at Centre for Intelligent Machine (CIM).

I have also worked at Mila as an intern with Dr. Doina Precup on NeurIPS MineRL competition 2019, where we explore learning transferable skills over multiple environments from the MineCraft gaming environment using imitation learning.

I completed my Under-graduation from Islamic University of Technology (IUT), Bangladesh. I had the pleasure of working on “Computational Nano-photonics” and was supervised by Dr. Md. Ruhul Amin and co-supervised by Dr. Rakibul Hasan Sagor.

Affiliations

Previously

News

  • March 2024. I’m joining Microsoft Research, Montreal as part-time research intern. I will be working on Multitask and Multimodal learning using LLM.
  • May, 2023- Aug, 2023. I worked at Microsoft Research, New York as Research Intern, on an Appiled RL project with John Langford and Alex Lamb.
  • October, 2021. Two papers got accepted in Offline Reinforcement Learning Workshop, NeurIPS 2021
    • “Importance of Empirical Sample Complexity Analysis for Offline Reinforcement Learning” - Paper
    • “Single-Shot Pruning for Offline Reinforcement Learning” - Paper
  • Sep, 2021- Aug 2022. I have worked at Ubisoft, Montreal with Joshua Romoff as Research Intern.
  • June, 2020. “Off-Policy Adversarial Inverse Reinforcement Learning” got accepted in Lifelong Learning workshop, ICML 2020. Paper, Code,Talk
  • January, 2020. I have started my Ph.D. at McGill University.
  • June, 2019. I joined Mila as Research Intern.
  • June, 2019. “Doubly Robust Estimators in Off-Policy Actor-Critic Algorithms” got accepted for spotlight presentation at RLDM 2019
  • January, 2018. I started my Master’s at McGill University.

Research Interest

  • Reinforcement Learning
  • Imitation Learning
  • Offline Reinforcement Learning
  • Representation learning
  • Multitask Learning
  • Generative Adversarial Networks
  • Hierarchical Reinforcement Learning