amromar99
I am a Machine Learning Engineer with a background in biomedical engineering. He has experience as a teaching assistant at Nile University and is
Nile UniversityCairo, Egypt
Pinned Repositories
Comprehensive-Analysis-of-Grid-World-Environment-Using-Monte-Carlo-Methods
This project compares four Monte Carlo methods in a Grid World environment, evaluating algorithms on rewards, sample efficiency, training time, state values, and policy effectiveness. It explores both deterministic and stochastic settings and examines the impact of the exploration parameter.
Finger-Movement-Classification-Using-EEG-signals
In this study, we aimed to classify finger movements using brain signals captured through EEG. We focused on five distinct classes of finger movements: Thumb, Index, Middle, Ring, and Pinky. Utilizing ML models (Machine Learning),CNN, RNN and hybrid approach CNN +Transformer
Reinforcement-Learning-Comparison-of-SARSA-and-DQN-Algorithms-
This project evaluates SARSA and Deep Q-Network (DQN) in the Frozen Lake environment, focusing on both deterministic and stochastic settings. It compares how each algorithm navigates the grid to reach a goal while avoiding hazards, highlighting their strengths and limitations in handling uncertainty and complexity.
SARSA-and-Q-Learning-Algorithms-in-a-Deterministic-Grid-World-Environment
This report compares SARSA and Q-learning in a 9x10 grid world. SARSA, "on-policy," converges quickly with ε=0.2, while Q-learning, "off-policy," performs well with ε=0.4. SARSA excels in reward and speed with lower ε, while Q-learning balances exploration and exploitation with higher ε.
amromar99's Repositories
amromar99/SARSA-and-Q-Learning-Algorithms-in-a-Deterministic-Grid-World-Environment
This report compares SARSA and Q-learning in a 9x10 grid world. SARSA, "on-policy," converges quickly with ε=0.2, while Q-learning, "off-policy," performs well with ε=0.4. SARSA excels in reward and speed with lower ε, while Q-learning balances exploration and exploitation with higher ε.
amromar99/Comprehensive-Analysis-of-Grid-World-Environment-Using-Monte-Carlo-Methods
This project compares four Monte Carlo methods in a Grid World environment, evaluating algorithms on rewards, sample efficiency, training time, state values, and policy effectiveness. It explores both deterministic and stochastic settings and examines the impact of the exploration parameter.
amromar99/Reinforcement-Learning-Comparison-of-SARSA-and-DQN-Algorithms-
This project evaluates SARSA and Deep Q-Network (DQN) in the Frozen Lake environment, focusing on both deterministic and stochastic settings. It compares how each algorithm navigates the grid to reach a goal while avoiding hazards, highlighting their strengths and limitations in handling uncertainty and complexity.
amromar99/Finger-Movement-Classification-Using-EEG-signals
In this study, we aimed to classify finger movements using brain signals captured through EEG. We focused on five distinct classes of finger movements: Thumb, Index, Middle, Ring, and Pinky. Utilizing ML models (Machine Learning),CNN, RNN and hybrid approach CNN +Transformer