Name: Ahmed Hendawy
Type: User
Company: Technical University of Darmstadt
Bio: PhD Candidate at LiteRL at TU Darmstadt.
My current research interests are Continual/ Lifelong, Multi-Task, and Meta-Learning for Deep Reinforcement Learning.
Twitter: AHendawy19
Location: Darmstadt, Germany
Blog: ahmedhendawy.de
Ahmed Hendawy's Projects
My Bachelor thesis which was conducted during my abroad study at TUM.
Official Python Implementation for "A Baseline for 3D Multi-Object Tracking"
A TensorFlow 2.0 implementation of an Age Regression algorithm. It is an assignment for the Deep Learning course at the University of Stuttgart.
A beautiful, simple, clean, and responsive Jekyll theme for academics
C++ library which contains algorithms for optimizations.
C++ concurrent program of a traffic simulation. The project uses the threads, mutex, locks as well as the message queues.
The implementations of the deep learning specialization's assignments.
A general 3D object detection codebse.
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
Dragon Ball Game is a Java implemented fighting game. The game was a course project for CS4 course at the German University in Cairo.
Simulation for different Real-life scenarios for a hybrid vehicle platoon controlled model
A neural network to generate captions for an image using CNN and RNN with BEAM Search.
Introduction to Deep Reinforcement Learning with Mushroom-RL
Python implementation for K-Nearest Neighbor applied on the iris dataset loaded from sklean. The code is an assignment of Machine Learning course at the University of Stuttgart.
An algorithm which solves the constrained optimization problem by reducing it to iterative unconstrained problem with undefined infeasible set.
C++ implementation of a Chatbot which uses ideas from the memory management techniques like smart pointers.
An open source robotics benchmark for meta- and multi-task reinforcement learning.
Official code of the paper "Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts"
Gemini is a modern LaTex beamerposter theme 🖼
A numerical approach to approximate the non linear MPC controller which is applied on a platooning application. Platoon is a group of vehicles with one leader vehicle and followers.
Benchmarking suite for MushroomRL Deep RL algorithms
Python implementation for the Naive Bayes algorithm applied on subset of SMS Spam Collection Dataset: https://archive.ics.uci.edu/ml/datasets/SMS+Spam+Collection. This is an assignment for the machine learning course at the university of stuttgart.