0

我将强化学习与神经网络 (DQN) 结合使用。我有一台配备 6 核 i7 和 AMD GPU 的 MacBook。TensorFlow 看不到 GPU，因此它会自动使用 CPU。当我运行脚本时，我在活动监视器中看到 CPU 利用率从大约 33% 变为 ~50%，即没有使用所有 CPU 内核。我的 TensorFlow 版本是 2.2.0。我试过了：

with tf.device("/cpu:0"):

我也想试试：

sess = tf.Session(config=tf.ConfigProto(intra_op_parallelism_threads=NUM_THREADS))

但我不明白如何使用“sess”来训练模型。

脚本每集运行大约需要 64 秒。我的问题：如何确保我的 python 脚本利用所有 CPU 内核，从而减少训练模型所需的时间。

制作模型的功能：

def OurModel(input_shape, action_space):
    X_input = Input(input_shape)

    # 'Dense' is the basic form of a neural network layer
    # Input Layer of state size(4) and Hidden Layer with 512 nodes
    X = Dense(512, input_shape=input_shape, activation="relu", kernel_initializer='he_uniform')(X_input)

            # Hidden layer with 256 nodes
    X = Dense(256, activation="relu", kernel_initializer='he_uniform')(X)

            # Hidden layer with 64 nodes
    X = Dense(64, activation="relu", kernel_initializer='he_uniform')(X)

            # Output Layer with # of actions: 2 nodes (left, right)
    X = Dense(action_space, activation="linear", kernel_initializer='he_uniform')(X)

    model = Model(inputs = X_input, outputs = X, name='CartPole DQN model')
    model.compile(loss="mse", optimizer=RMSprop(lr=0.00025, rho=0.95, epsilon=0.01), metrics=["accuracy"])

包含 model.fit 和 model.predict 的函数

def act(self, state):
        if np.random.random() <= self.epsilon:
            return random.randrange(self.action_size)
        else:
            return np.argmax(self.model.predict(state))

和

def replay(self):
        if len(self.memory) < self.train_start:
            return
        # Randomly sample minibatch from the memory
        minibatch = random.sample(self.memory, min(len(self.memory), self.batch_size))

        state = np.zeros((self.batch_size, self.state_size))
        next_state = np.zeros((self.batch_size, self.state_size))
        action, reward, done = [], [], []

        # do this before prediction
        # for speedup, this could be done on the tensor level
        # but easier to understand using a loop
        for i in range(self.batch_size):
            state[i] = minibatch[i][0]
            action.append(minibatch[i][1])
            reward.append(minibatch[i][2])
            next_state[i] = minibatch[i][3]
            done.append(minibatch[i][4])

        # do batch prediction to save speed
        target = self.model.predict(state)
        target_next = self.model.predict(next_state)

        for i in range(self.batch_size):
            # correction on the Q value for the action used
            if done[i]:
                target[i][action[i]] = reward[i]
            else:
                # Standard - DQN
                # DQN chooses the max Q value among next actions
                # selection and evaluation of action is on the target Q Network
                # Q_max = max_a' Q_target(s', a')
                target[i][action[i]] = reward[i] + self.gamma * (np.amax(target_next[i]))

        # Train the Neural Network with batches
        self.model.fit(state, target, batch_size=self.batch_size, verbose=0)

让我知道是否需要更多代码。请回答我。谢谢你。

4

0 回答 0