Training the network

Now, we will see how to train the network.

First, we define the DQN class and initialize all variables in the __init__ method:

class DQN(object):
    def __init__(self, state_size,
                       action_size,
                       session,
                       summary_writer = None,
                       exploration_period = 1000,
                       minibatch_size = 32,
                       discount_factor = 0.99,
                       experience_replay_buffer = 10000,
                       target_qnet_update_frequency = 10000,
                       initial_exploration_epsilon = 1.0,
                       final_exploration_epsilon = 0.05,
                       reward_clipping = -1,
                        ):

Initialize all variables:

        self.state_size = state_size
        self.action_size = action_size


        self.session = session
        self.exploration_period = float(exploration_period)
        self.minibatch_size = minibatch_size
  ...