ddpg.py 文件源码

def __init__(self, config):
        """initialized approximate value function

        config should have the following attributes

        Args:
            device: the device to use computation, e.g. '/gpu:0'
            gamma(float): the decay rate for value at RL
            history_length(int): input_length for each scale at CNN
            n_feature(int): the number of type of input 
                (e.g. the number of company to use at stock trading)
            trade_stock_idx(int): trading stock index
            gam (float): discount factor
            n_history(int): the nubmer of history that will be used as input
            n_smooth, n_down(int): the number of smoothed and down sampling input at CNN
            k_w(int): the size of filter at CNN
            n_hidden(int): the size of fully connected layer
            n_batch(int): the size of mini batch
            n_epochs(int): the training epoch for each time
            update_rate (0, 1): parameter for soft update
            learning_rate(float): learning rate for SGD
            memory_length(int): the length of Replay Memory
            n_memory(int): the number of different Replay Memories
            alpha, beta: [0, 1] parameters for Prioritized Replay Memories
            action_scale(float): the scale of initialized ation
        """
        self.device = config.device
        self.save_path = config.save_path
        self.is_load = config.is_load
        self.gamma = config.gamma
        self.history_length = config.history_length
        self.n_stock = config.n_stock
        self.n_smooth = config.n_smooth
        self.n_down = config.n_down
        self.n_batch = config.n_batch
        self.n_epoch = config.n_epoch
        self.update_rate = config.update_rate
        self.alpha = config.alpha
        self.beta = config.beta
        self.lr = config.learning_rate
        self.memory_length = config.memory_length
        self.n_memory = config.n_memory
        self.noise_scale = config.noise_scale
        self.model_config = config.model_config
        # the length of the data as input
        self.n_history = max(self.n_smooth + self.history_length, (self.n_down + 1) * self.history_length)
        print ("building model....")
        # have compatibility with new tensorflow
        tf.python.control_flow_ops = tf
        # avoid creating _LEARNING_PHASE outside the network
        K.clear_session()
        self.sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True, log_device_placement=False))
        K.set_session(self.sess)
        with self.sess.as_default():
            with tf.device(self.device):
                self.build_model()
        print('finished building model!')