dqn_8_exp.py 文件源码

def __init__(self):
        # init some parameters
        self.replay_buffer = deque()

        self.time_step = 0

        self.epsilon = START_EPSILON

        self.state_dim = input_dim

        self.action_dim = num_output

        #initialize weights and biases of deep q net
        self.weights = {
            'w1': tf.Variable(tf.random_normal([3, 3, 2, 150])),
            'w2': tf.Variable(tf.random_normal([1, 1, 150, 1])),
            'w3': tf.Variable(tf.random_normal([3,3,1,10])),
            'out': tf.Variable(tf.random_normal([dim*dim*10, num_output]))
        }

        self.biases = {
            'b1': tf.Variable(tf.random_normal([150])),
            'b2': tf.Variable(tf.random_normal([1])),
            'b3': tf.Variable(tf.random_normal([10])),
            'out': tf.Variable(tf.random_normal([num_output]))
        }
        self.state_input = tf.placeholder("float",[None, self.state_dim[0] * self.state_dim[1], 2])
        keep_prob = tf.placeholder(tf.float32) # dropout probability

        #create deep q network
        self.deep_q_network(self.state_input, self.weights, self.biases, keep_prob)
        self.training_rules()

        # Initialize session
        self.session = tf.InteractiveSession()
        self.session.run(tf.initialize_all_variables())

        # saver
        self.saver = tf.train.Saver()