• 🔭 I’m currently studying Computational Statistics and Machine Learning at University College London (UCL).

• 🌱 Ongoing projects:

  • Contributing to Syllabus by implementing Curriculum Learning algorithms (e.g. Self-Play variants).
  • Contributing to Stoix by implenting DQN variants in JAX.

• 📝 I regularly write about Reinforcement Learning and other ML topics on Towards Data Science

• 📫 Reach me here: ryan.pegoud@outlook.com

• 📄 Learn more about my experiences on my portfolio

• 🤝 Connect with me on LinkedIn

Latest Blogs Posts

• Rainbow: The Colorful Evolution of Deep Q-Networks
• A Practical Guide to Proximal Policy Optimization in JAX
• A Gentle Introduction to Deep Reinforcement Learning in JAX
• Implementing a Transformer Encoder from Scratch with JAX and Haiku
• Vectorize and Parallelize RL Environments with JAX: Q-learning at the Speed of Light⚡

---

🕹️ Languages and Tools

---