This repository documents my journey to understand reinforcement learning fundamentals. I aim to implement core RL algorithms and seminal research papers, one step at a time.
Through hands-on coding and analysis, I hope to gain intuition about:
- Key RL concepts like Markov decision processes, dynamic programming, temporal difference learning, etc.
- Foundational algorithms like Q-Learning, SARSA, Policy Gradients
- Influential innovations like Deep Q Networks, Trust Region Policy Optimization
I plan to thoroughly comment each implementation and summarize the key ideas behind major advancements. Over time, I hope this repository becomes a pedagogical tool for anyone looking to learn about RL.
Feedback and suggestions to improve this repository are welcome. This is very much a work in progress document of my own learning.