CartPole_DRQN.py 文件源码

def xavier_initializer(shape):
    dim_sum = np.sum(shape)
    if len(shape) == 1:
        dim_sum += 1
    bound = np.sqrt(2.0 / dim_sum)
    return tf.random_uniform(shape, minval=-bound, maxval=bound)

# # Assigning network variables to target network variables 
# def assign_network_to_target():
#   update_wfc = tf.assign(w_fc_target, w_fc)
#   update_bfc = tf.assign(b_fc_target, b_fc)

#   sess.run(update_wfc)
#   sess.run(update_bfc)

#   cell_target = cell 

# Input