DQN
DQN is Q-Learning with a neural network that can look at a game screen.
What it does
DQN is Q-Learning with a neural network that can look at a game screen.
Deep Network: Complex AI brain • State: Current game screen
How it works
- Look at the current screen or state.
- Use a neural network to estimate good actions.
- Choose an action that should lead to more reward.
Uses & Applications
- A game AI can learn from pixels in an Atari-style game.
- A robot simulator can learn actions from screen-like views.
- A training system can test choices in a safe virtual world.
In short
DQN combines Q-Learning with deep learning.
Try it yourself
Teach a neural player to reach the goal
A small network remembers moves and rewards. It practices on those memories to learn which way to go.
Your turn
Change one setting at a time. Reset example puts everything back.
Map a screen state to action values
Step 1Why this happens