Welcome to my personal journey through the Hugging Face Deep Reinforcement Learning Course! This repository serves as my digital logbook 📓, where I track my progress, store completed assignments 📝, and share insights and challenges I encounter along the way
This course is a deep dive into the fascinating world of Deep Reinforcement Learning (DRL) 🤖. It covers everything from the basics to more advanced topics, with hands-on practice in unique environments and the opportunity to participate in exciting challenges 🏆
- Comprehensive learning on Deep RL theory and practice 📚.
- Hands-on experience with leading Deep RL libraries 🧠.
- Training agents in diverse environments 🌍.
- Participation in challenges and community engagement 👥.
- Opportunity to earn a certificate of completion or honors 🏅.
Below is the breakdown of the course units and my completion status:
- UNIT 0: Welcome to the Course 🎉
- Setup
- Discord 101
- UNIT 1: Introduction to Deep Reinforcement Learning 📘
- BONUS UNIT 1: Introduction to Deep RL with Huggy 🐶
- LIVE 1: Course Mechanics, Q&A, and Playing with Huggy 🎙️
- UNIT 2: Introduction to Q-Learning 🧩
- UNIT 3: Deep Q-Learning with Atari Games 🕹️
- BONUS UNIT 2: Automatic Hyperparameter Tuning with Optuna 🔧
- UNIT 4: Policy Gradient with PyTorch 🔥
- UNIT 5: Introduction to Unity ML-Agents 🤖
- UNIT 6: Actor Critic Methods with Robotics Environments 🤖🔬
- UNIT 7: Introduction to Multi-Agents and AI vs AI 👾
- UNIT 8: Proximal Policy Optimization (PPO) 📈
- Part 1: PPO
- Part 2: PPO with Doom
- BONUS UNIT 3: Advanced Topics in Reinforcement Learning 🧠
- Certification and Congratulations 🎓
- Google Colab for hands-on practice.
- Discord for community interaction and support.
- Hugging Face Account for model sharing and challenges.
I aim to complete at least 80% of the assignments to earn the course completion certificate. Here, I'll track the assignments submitted and the overall progress toward this goal.
Feel free to explore this repository to see my progress, learn from the challenges I faced, and use my solutions as a learning resource. I hope my journey can inspire and help others on the same path.
If you have any suggestions, feedback, or questions about my work, please feel free to open an issue or submit a pull request.
A huge thanks to the Hugging Face team and the course instructors for providing this incredible learning opportunity.
This README is a living document and will be updated regularly as I progress through the Hugging Face Deep Reinforcement Learning Course. 🔄