📄️ Maze Navigation: From Classical Algorithms to Reinforcement Learning
Maze navigation is a fundamental problem in computer science and artificial intelligence. This example demonstrates the progression from classical graph search algorithms (BFS, DFS, Dijkstra) to reinforcement learning, and explains why RL is necessary when the environment is unknown or dynamic.
📄️ The Inverted Pendulum (CartPole)
The Inverted Pendulum (or CartPole) is a classic problem in control theory and reinforcement learning. The goal is to balance a pole on a moving cart by applying forces to the cart (left or right).
📄️ Marketing Budget Allocation: Manual vs Reinforcement Learning
How do you allocate a limited marketing budget across multiple channels when you don't know which ones perform best? This example compares manual allocation (equal split) with reinforcement learning that learns and optimizes automatically.