Skill Level Intermediate
- [Narrator] Have you heard of Artificial Intelligence systems that can play games better than you and I? Games like golf, chess, pawn and StarCraft too became popular because of the groundbreaking research in the artificial intelligence space. In the game of golf for example, an AI algorithm was the first to defeat of professional human player. You may be following news about AI systems in real world use cases, like self-driving cars, finance, robotics and chemistry. It's also used for better personalized recommendations and has many other use cases. All of this have made possible or improved with reinforcement learning. You may be a machine learning developer trying to apply a reinforcement learn techniques to your project, a researcher trying to implement a reinforcement learning algorithm, a product manager who wants to understand your team better, or you're just very intrigued by reinforcement learning. Whichever category you belong to, this course is well fit to give you a detailed and friendly introduction to the topic. I'm Khaulat, currently a machine machine-learning developer, who loves to teach and research machine learning. I founded an Artificial Intelligence community, AI Abeokuta to help newbies and enthusiasts learn about AI and also provide a platform for practitioners in the field to network. It hasn't stopped growing ever since and has helped many transition to the field. I also organize and speak at different TechniTalks. I look forward to taking through this journey of understanding the basics of reinforcement learning. I'll be covering the Monte-Carlo method and the temporary difference methods which includes SARSA, Q-learning and Expected SARSA. This methods are the foundation of reinforcement learning. And finally, I want to help you have meaningful conversations whenever reinforcement learning is being discussed. So let's dive right in.