Deep Q-Learning
The DeepMind group combined this with deep neural networks to create a system that could learn to play Atari video games.
What is reinforment learning? (Q-learning)
What was the name of the engineer that joined IBM’s laboratory to program a computer to play checkers?
Who is Arthur Samuel?
What game poses an extreme problem for game tree style AIs use to exponential possibilities?
What is Go?
What was the Name of the AI that DeepMind used to play Atari Video Games
What is Deep Q-Network (DQN)
How did Samuel’s checker AI predict potential moves?
What is making a game tree?
What amount of game experience did AlphaGo Zero start with?
What is Zero?
The Deep Q-Network learned to play this Atari video game 5 times better than human players.
What is Atari Breakout?
What is a drawback of using a game tree?
What is Exponential outcomes?
How did programers solve Go?
What is Monte Carlo Tree search?
What does reinforcment learning require a balance between
What is exploration and exploitation?
How does the AI solve exponential explosion?
What is using players current board passion and generatiating a smaller game tree?
How did the Monte Carlo tree search affect the AI?
What is assigning new probabilities to all possible moves that lead to wins or losses?