Reinforcement Learning Basics

20 lessons in AI Fundamentals

• Sampling From a Stochastic PolicyCode Quiz
• Q-Table Initialization and IndexingCode Quiz
• States, Actions, and Rewards DefinedSlides / Video
• Policy: Mapping States to ActionsSlides / Video
• States, Actions, and Rewards DefinedSlides / Video
• Agent, Environment, and Interaction LoopSlides / Video
• Real-World Applications of RLSlides / Video
• Reward Shaping and Reward DesignSlides / Video
• The Credit Assignment ProblemSlides / Video
• Episodic vs Continuing TasksSlides / Video
• On-Policy vs Off-Policy LearningSlides / Video
• Temporal Difference Learning ConceptSlides / Video
• Q-Learning as a Basic RL AlgorithmSlides / Video
• Model-Based vs Model-Free RLSlides / Video
• Markov Decision Process: The RL FrameworkSlides / Video
• Epsilon-Greedy Action SelectionSlides / Video
• Exploration vs Exploitation TradeoffSlides / Video
• Value Functions: State and Action (Q)Slides / Video
• Discount Factor in Reinforcement LearningSlides / Video
• Reward Signal vs Long-Term ReturnSlides / Video