Esraa Elelimy
I am a PhD student at the RLAI lab advised by Martha White.
I received my M.Sc. in Computing Science from the University of Alberta where I worked on efficient real-time recurrent learning approaches for online learning. Before this, I worked as an algorithms engineer at Valeo, focusing on perception algorithms for self-driving car applications. I did my undergrad at Zewail City, where I majored in aerospace engineering.
Research Interests
My research interests lie primarily in online reinforcement learning, and continual learning.
Publications
-
Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy
Matthew Vandergrift, Esraa Elelimy, Martha White (ICML 2026)
-
Forager: a lightweight testbed for continual learning with partial observability in RL
Steven Tang, Xinze Xiong, Anna Hakhverdyan, Andrew Patterson, Jacob Adkins, Jiamin He, Esraa Elelimy, Parham Mohammad Panahi, Martha White, Adam White (RLJ 2026)
-
Investigating the Histogram Loss in Regression
Ehsan Imani, Kai Luedemann, Sam Scholnick-Hughes, Esraa Elelimy, Martha White (JMLR 2026)
-
Rethinking the Foundations for Continual Reinforcement Learning
Esraa Elelimy, David Szepesvari, Martha White, Michael Bowling (RLJ 2025)
-
Deep Reinforcement Learning with Gradient Eligibility Traces🏆 Outstanding Paper Award on The Theory of Reinforcement Learning
Esraa Elelimy*, Brett Daley*, Andrew Patterson, Marlos C. Machado, Adam White, Martha White (RLJ 2025)
-
Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
Esraa Elelimy, Adam White, Michael Bowling, Martha White (NeurIPS 2024)
-
AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning
Subhojeet Pramanik, Esraa Elelimy, Marlos C Machado, Adam White (TMLR 2024)
-
Time Synchronization for Automotive Prototyping and Testing Platforms
Esraa Elelimy, Andrew Azmy (AINA 2021)
Workshops & Abstracts
-
Hidden Tuning is Misleading The RL Community
Esraa Elelimy, Matthew Vandergrift, Anna Hakhverdyan, Andrew Patterson, Michael Bowling, Adam White, Martha White (Finding the Frame @ RLC 2026)
-
Long-Horizon Prediction of Solar Wind Events with Reinforcement Learning
Esraa Elelimy, Jacob Adkins, Adam White, Abigail R. Azari (ML-Helio 2025)
-
Rethinking the Foundations for Continual Reinforcement Learning
Michael Bowling, Esraa Elelimy (RLDM 2025, extended abstract)
News
- Silver reviewer award at ICML 2026.
- Received the Alberta Graduate Excellence Scholarship (AGES).
- Joined RBC Borealis as an AI Research Intern.
- Outstanding Paper Award (Theory of RL) at RLJ 2025 for our work on gradient eligibility traces.
- Received the Alberta Graduate Excellence Scholarship (AGES).
- Defended my M.Sc. thesis on Real-Time Recurrent Learning with Complex-valued Trace Units.
- Started my PhD at the RLAI lab.