April 24, 2026
Reinforcement Learning: An Introduction
Notes
The RL bible. Bandits to policy gradients to planning.
Browse posts by tag
The RL bible. Bandits to policy gradients to planning.
Mathematical RL fundamentals (MDPs, value functions, dynamic programming, approximate methods). RL foundational text that bridges theory and practice.
Intelligence as utility maximization under uncertainty. A unifying framework connecting A* search, reinforcement learning, Bayesian networks, and MDPs.