MathFoundationRL/Book-Mathematical-Foundation-of-Reinforcement-Learning

Provides rigorous mathematical treatment of RL fundamentals—from Markov decision processes and Bellman equations through value iteration, policy iteration, and Monte Carlo learning—with carefully calibrated depth and pedagogical design using a consistent grid-world example throughout. Combines Springer-published textbook content with freely available LaTeX slide sources and comprehensive lecture videos (in English and Chinese) covering ten sequentially-organized chapters bridging basic mathematical tools and classical algorithms.

14,922 stars. Actively maintained with 1 commit in the last 30 days.