Ahmed M. Hendawy

Ph.D. Candidate at LiteRL and IAS research groups, TU Darmstadt.

prof_pic.jpg

I am a third-year PhD. student at the LiteRL and IAS research groups at TU Darmstadt, Germany. My advisors are Prof. Carlo D’Eramo and Prof. Jan Peters. I have a master’s degree in Information Technology from the University of Stuttgart, with a specialization in Computer Engineering. In 2019, I graduated from the German University in Cairo (GUC) with a bachelor’s degree in Mechatronics Engineering.

My research delves into the Reinforcement Learning topics of multi-task and continual learning. My research objective is to boost the learning process of agents by leveraging knowledge from multiple tasks learned concurrently or in sequence. I develop RL algorithms that are application agnostic; however, I lean towards robot learning applications.

news

Mar 25, 2025 Our Workshop on Inductive Biases in Reinforcement Learning (IBRL) 🚀 has been accepted at RLC 2025.
Aug 21, 2024 Our survey “Machine Learning with Physics Knowledge for Prediction: A Survey” is out.
Jan 17, 2024 Our work “Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts” has been accepted at ICLR 2024 for a poster presentation.
Oct 22, 2023 Our work “Using Proto-Value Functions for Curriculum Generation in Goal-Conditioned RL” has been accepted at the NeurIPS 2023 Workshop on Goal-Conditioned Reinforcement Learning.
Oct 18, 2023 Our work “Parameter-efficient Tuning of Pretrained Visual-Language Models in Multitask Robot Learning” has been accepted at the CoRL 2023 Workshop on Learning Effective Abstractions for Planning (LEAP).
Feb 16, 2023 I was selected as one of the top 10% of reviewers who volunteered in AISTATS 2023.

latest posts

selected publications

  1. physicsMLSurvey.png
    Machine Learning with Physics Knowledge for Prediction: A Survey
    Joe Watson ,  Chen Song ,  Oliver Weeger , and 8 more authors
    arXiv preprint arXiv:2408.09840, 2024
  2. moore.png
    Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
    A. Hendawy ,  J. Peters ,  and  C. D’Eramo
    2024
  3. corl_leap_paper.png
    Parameter-efficient Tuning of Pretrained Visual-Language Models in Multitask Robot Learning
    M. Mittenbuehler ,  A. Hendawy ,  C. D’Eramo , and 1 more author
    2023
  4. crpi.png
    Using Proto-Value Functions for Curriculum Generation in Goal-Conditioned RL
    H. Metternich ,  A. Hendawy ,  P. Klink , and 2 more authors
    2023
  5. L3D-IVU
    CFA: Constraint-based Finetuning Approach for Generalized Few-Shot Object Detection
    K. Guirguis ,  A. Hendawy ,  G. Eskandar , and 3 more authors
    2022