Arushi Jain

I am fifth year Computer Science (Artificial Intelligence) Ph.D. candidate with Doina Precup at McGill University and Mila, Montreal , Canada.

I am interning at Microsoft Research (MSR) in Amsterdam, hosted by Elise Van Der Pol, where I am working on Molecular Drug Discvery! Prior, I interned in Fall 2022 at Meta AI Research Lab (FAIR) in Paris, hosted by Alessandro Lazaric, where I worked on self-supervised framework integrating exploration and representation in a reward-free zero-shot setting.

I completed my Masters at McGill University and Mila, with Doina Precup. I previously worked as a Research Fellow at Microsoft Research (MSR) India with Sundararajan Sellamanickam . My Bachelor's in Computer Science is from IIIT-Delhi India.

Research Summary: I am interested in advancing the reliability of reinforcement learning systems for real-world applications. I explore innovative optimization techniques to ensure consistent and safe behaviors while bridging insights from various fields to enrich RL. My work also delves into the fusion of representation learning and exploration strategies, and the personalization potential of large language models (LLMs).

Email  /  CV  / Google Scholar  /  Twitter  /  Github

profile photo
Highlights and News
Research

My research focuses on learning safe reinforcement learning (RL) algorithms grounded in theory which can be extended to the real-world applications. I am also interested in off-policy RL and Constrained MDPs (CMDPs).

3DSP GVFExplorer: Adaptive Exploration for Data-Efficient General Value Function Evaluations
Arushi Jain, Josiah P. Hanna, Doina Precup
Under Submission, 2024
Paper
3DSP Towards Painless Policy Optimization for Constrained MDPs
Arushi Jain, Sharan Vaswani, Reza Babanezhad, Csaba Szepesvari, Doina Precup
UAI and RLDM, 2022
paper / short RLDM paper / code / RLDM poster
3DSP Variance Penalized On-Policy and Off-Policy Actor-Critic
Arushi Jain, Gandharv Patil, Ayush Jain, Khimya Khetarpal, Doina Precup
AAAI, 2021
paper / code / talk / slides / poster
3DSP Safe Option-Critic: Learning Safety in the Option-Critic Architecture
Arushi Jain*, Khimya Khetarpal*, Doina Precup
Knowledge Engineering Review (KER) Journal, 2021. (Cambridge University Press Journal)
Adaptive Learning Agents (ALA) Workshop, ICML, 2018.
paper / code / slides / poster
3DSP Safety using Constraint Variance in Policy-Gradient Methods
Arushi Jain
Master's thesis, McGill University, March 2020.
paper
3DSP Safe Actor-Critic
Arushi Jain*, Ayush Jain, Doina Precup
Safety, Risk and Uncertainty in RL Workshop, UAI, 2018.
Women in ML (WiML) Workshop, NeurIPS , 2018.
paper / / slides / poster
3DSP Safe Hierarchical Policy Optimization using Constrained Return Variance in Options
Arushi Jain*, Doina Precup
RLDM, 2019.
paper
3DSP Learning Options using Constrained Return Variance
Arushi Jain*, Doina Precup
Safety and Robustness in Decision Making Workshop , NeurIPS, 2019.
paper / poster
3DSP Safe Policy Learning with Constrained Return Variance
Arushi Jain*
Graduate Student AI Symposium, Canadian AI Conference, 2019.
Proceeding published in LNAI Series by Springer Verlag.
paper / talk
Reviewer
sym Reviewer, DARL, ICML Workshop ('22)

Reviewer, AISTATS ('22)

Reviewer, ICLR ('22), ML Evaluation Standards Workshop

Reviewer, NeurIPS ('18), WiML Workshop


Source code and style from Jon Barron's website.