Ahmed Hendawy
Research Interests
Reinforcement Learning, Decision-Making, Multi-task Reinforcement Learning, Continual/ Lifelong Reinforcement Learning
Affiliations
- TU Darmstadt, Intelligent Autonomous Systems, Computer Science Department
- Hessian Centre for Artificial Intelligence
Contact
ahmed.hendawy@tu-darmstadt.de
Room E327, Building S2|02, TU Darmstadt, FB-Informatik, FG-IAS, Hochschulstr. 10, 64289 Darmstadt
+49-6151-16-25371
Ahmed Hendawy joined the Intelligent Autonomous Systems Group at TU Darmstadt as a Ph.D. Student in April 2022. He is working on Multi-Task and Continual Reinforcement Learning, supervised by Dr. Carlo D'Eramo (as part of the LiteRL research group).
Ahmed Hendawy has a master's degree in Information Technology from the University of Stuttgart, with a specialization in Computer Engineering. In 2019, Ahmed graduated from the German University in Cairo (GUC) with a bachelor's degree in Mechatronics Engineering.
Reviewing
ICML, ICLR, Neurips, EWRL, RLC, CORL, AISTATS (Top Reviewer).
Teaching Assistant
| Lecture | Years |
| Reinforcement Learning | SS 2022, SS 2023 |
His master's thesis, “Constraint-based Optimization Approach for Generalized Few-Shot Object Detection”, was awarded the Sony Award for best master’s thesis at the University of Stuttgart. In addition, his work, "CFA: Constraint-based Finetuning Approach for Generalized Few-Shot Object Detection", was recognized by the Best Paper Runner-up Award in the CVPR 2022 Workshop on Limited Labelled Data for Image and Video Understanding (L3D-IVU).
Ahmed Hendawy has served as a reviewer for the Conference on Robot Learning (CoRL) 2023 and AISTATS 2023. His effort was recognized by the Top Reviewer Award at AISTATS 2023. Ahmed Hendawy takes great pleasure in instructing students as a teaching assistant in the Reinforcement Learning course (in the summer semester of 2023 and 2022), in addition to research project supervision of integrated projects (e.g. Latent Generative Replay in Continual Learning, and Memory-free Continual Reinforcement Learning).
Talks and Interviews
- Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts @ Machine Learning and AI Academy (2024)
- Introduction to Reinforcement Learning @ To Data and Beyond Podcast (2024) (in Arabic)
- Building Deep Reinforcement Learning Applications @ To Data and Beyond Podcast (2024) (in Arabic)
Publications
- Hendawy, A.; Peters, J.; D'Eramo, C. (2024). Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts, International Conference on Learning Representations (ICLR).
- Guirguis, K.; Abdelsamad, M.; Eskandar, G.; Hendawy, A.; Kayser, M.; Yang, B.; Beyerer, J. (2023). Towards Discriminative and Transferable One-Stage Few-Shot Object Detectors, Winter Conference on Applications of Computer Vision (WACV) 2023.
- Mittenbuehler, M.; Hendawy, A.; D'Eramo, C.; Chalvatzaki, G. (2023). Parameter-efficient Tuning of Pretrained Visual-Language Models in Multitask Robot Learning, CoRL 2023 Workshop on Learning Effective Abstractions for Planning (LEAP).
- Metternich, H.; Hendawy, A.; Klink, P.; Peters, J.; D'Eramo, C. (2023). Using Proto-Value Functions for Curriculum Generation in Goal-Conditioned RL, NeurIPS 2023 Workshop on Goal-Conditioned Reinforcement Learning.
- Guirguis, K.; Hendawy, A.;Eskandar, G.;Abdelsamad, M.;Kayser, M.;Beyerer, J. (2022). CFA: Constraint-based Finetuning Approach for Generalized Few-Shot Object Detection, Workshop on Learning with Limited Labelled Data for Image and Video Understanding (L3D-IVU).