Main idea
Uses a DQN instead of a Q-table compared to Q-Learning. This neural network will approximate, given a state, the different Q-values for each possible action at that state. And that’s exactly what Deep Q-Learning does.
Uses a DQN instead of a Q-table compared to Q-Learning. This neural network will approximate, given a state, the different Q-values for each possible action at that state. And that’s exactly what Deep Q-Learning does.