A collection of short, mathematical notes on reinforcement learning, optimization, and the ideas behind learning algorithms.

• Why Do Neural TD Converge ? — June 02, 2026
• Function Approximation in RL: From Tables to Linear Models to Neural Networks — May 27, 2026
• The Beauty of a Simple Proof: TD Learning Without Projection — May 26, 2026
• Stochastic Gradient Descent: Why Randomness Works — May 13, 2026
• Why Gradient Descent Works: A Small Mathematical Story — May 12, 2026
• Why Vanilla Q-Learning Breaks Under Corrupted Rewards — April 12, 2026