Skip to content
View Edward-Eughene-Timothy's full-sized avatar
:shipit:
Grinding
:shipit:
Grinding

Block or report Edward-Eughene-Timothy

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

πŸ‘‹ Hello, I’m Edward Eughene Timothy

Fedora Linux Field: AI Engineering License: GPL v3


πŸ§‘β€πŸ’» About Me

I’m an undergraduate AI Engineering student driven by curiosity and creativity in the field of artificial intelligence. I focus on building practical, efficient, and meaningful AI projects that blend deep learning and reinforcement learning techniques with real-world applications.


πŸ” Areas of Interest

  • Machine Learning & Deep Learning
  • Reinforcement Learning (Gymnasium, PPO, DQN)
  • Computer Vision & Perception
  • Fine-Tuning Local Language Models (LLMs)
  • Efficient Model Training & Deployment
  • Python and R Programming

🚧 Ongoing Projects

  • 🏎️ Self-Driving Car Agent β€” PPO-trained agent in CarRacing-v3 using visual inputs
  • 🧠 Local AI Assistant β€” Custom LLM companion using Gemma + Unsloth
  • 🚦 Smart Traffic Controller β€” RL-driven traffic light simulation in Python
  • πŸ“Š Academic R Toolkit β€” R solutions and visualizations for coursework

πŸ“š Currently Learning

  • Advanced RL algorithms & Gymnasium wrappers
  • Japanese language and pop culture πŸ‡―πŸ‡΅
  • Local model fine-tuning & prompt engineering
  • AI deployment on limited hardware (CPU-first mindset)

🀝 Open to Collaborating On

  • Reinforcement learning projects
  • Vision or simulation-based AI systems
  • Fine-tuned personal assistant LLMs

πŸ“« Reach Me


β€œBuild, experiment, and learn β€” the AI way.”

Popular repositories Loading

  1. DQN-RL-for-Hikikomori-Reintegration DQN-RL-for-Hikikomori-Reintegration Public

    Reinforcement Learning-based DQN model for helping Hikikomori reintegrate into society through a gamified system. The AI agent selects tasks of varying difficulty to encourage gradual social engage…

    2

  2. CONFLICT-RESOLUTION-ASSISTANT CONFLICT-RESOLUTION-ASSISTANT Public

    Jupyter Notebook

  3. Reinforcement-learning-with-Deep_Learning-for-Cartpole-Balancing Reinforcement-learning-with-Deep_Learning-for-Cartpole-Balancing Public

    This project was done to have a clear understanding about the Reinforcement Learning Concept

    Jupyter Notebook

  4. ML-and-DataScience-Practice-Problems ML-and-DataScience-Practice-Problems Public

    for practice purposes

    Jupyter Notebook

  5. Walmart-Sales-Prediction Walmart-Sales-Prediction Public

    project to get deep understanding on the ML algorithms

    Jupyter Notebook

  6. Red-Wine-Quality-Prediction Red-Wine-Quality-Prediction Public

    made this for better understanding of regression

    Jupyter Notebook