REINFORCEMENT LEARNING

introduction basic structure key feature of reinforcement learning Review: Probaility and Random Variable Review: Poisson and Exponential Distribution Review: Independence, Correlation, Conditional Probability Uncorrelated 안에 independent 가 있다. x y p 0 0 0.25 1 1 0.25 1 1 0.25 2 0 0.25 Multi Armed Bandit Bandits (또는 Multi-Arm Bandits, Read more…