Hands-On Artificial Intelligence for IoT

Dueling DQN

Dueling DQN decouples the Q-function into the value function and advantage function. The value function is the same as discussed earlier ; it represents the value of the state independent of action. The advantage function, on the other hand, provides a relative measure of the utility (advantage/goodness) of action a in the state s:

In Dueling DQN, the same convolutional is used to extract features but, in later stages, it's separated into two separate networks, one providing the value and another providing the advantage. Later, the two stages are recombined using an aggregating layer to estimate the Q-value. This ensures that the ...