A 4.3.6 / A 4.3.7 Reinforcement Learning & Genetic Algorithms
A4.3.6 covers reinforcement learning, where agents learn decisions by interacting with their environment, based on cumulative reward, actions, states, rewards, policies, and the exploration vs. exploitation trade-off. A4.3.7 describes genetic algorithms, applied in optimisation problems like route planning (travelling salesperson problem), using concepts like population, fitness, selection, crossover, mutation,...