Hands-On Artificial Intelligence for Beginners

Training the network

We'll give our training function a simple name: train. First, we'll feed it mini-batches of data from the replay memory:

def train(self):    ''' Training procedure for the Q Network'''    minibatch = random.sample(self.replayBuffer, 32)    stateBatch = [data[0] for data in minibatch]    actionBatch = [data[1] for data in minibatch]    rewardBatch = [data[2] for data in minibatch]    nextBatch = [data[3] for data in minibatch]

Next, we'll calculate the Q-value for each batch:

batch = []    qBatch = self.QValueT.eval(feed_dict = {self.inputValT: nextBatch})    for i in range(0, 32):      terminal = minibatch[i][4]      if terminal:        batch.append(rewardBatch[i])      else:        batch.append(rewardBatch[i] + self.gamma * np.max(qBatch[i]))

Now, let's bind this all together ...