Up Next
Back to Show
Crash Course: Artificial Intelligence
Reinforcement Learning #9
Season 1
Episode 9
Reinforcement learning is useful in situations where we want to train AIs to have certain skills we don’t fully understand. We’re going to explore these ideas, introduce a ton of new terms like value, policy, agent, environment, actions, and states and we’ll show you how we can use strategies like exploration and exploitation to train John Green Bot to find things more efficiently next time.
Sign up now for inspiring and thought-provoking media delivered straight to your inbox.
Support Provided By
12:31
One of the most common ways we interact with computers is through language
11:41
We’re moving on from artificial intelligence that needs training labels.
16:56
John Green Bot wrote his first novel!
12:08
We’re going to talk about backpropagation.
11:29
We're combining the artificial neuron we created into an artificial neural network.
14:57
We’re going to teach John Green Bot how to tell the difference between donuts and bagels.
11:25
What Is Artificial Intelligence?