教程 | 深度强化学习入门：用TensorFlow构建你的第一个游戏AI

class ExperienceReplay(object):
    """
    During gameplay all the experiences < s, a, r, s’ > are stored in a replay memory. 
    In training, batches of randomly drawn experiences are used to generate the input and target for training.
    """
    def __init__(self, max_memory=100, discount=.9):
        """
        Setup
        max_memory: the maximum number of experiences we want to store
        memory: a list of experiences
        discount: the discount factor for future experience
        
        In the memory the information whether the game ended at the state is stored seperately in a nested array
        [...
        [experience, game_over]
        [experience, game_over]
        ...]
        """
        self.max_memory = max_memory
        self.memory = list()
        self.discount = discount

    def remember(self, states, game_over):
        #Save a state to memory
        self.memory.append([states, game_over])
        #We don't want to store infinite memories, so if we have too many, we just delete the oldest one
        if len(self.memory) > self.max_memory:
            del self.memory[0]

    def get_batch(self, model, batch_size=10):
        
        #How many experiences do we have?
        len_memory = len(self.memory)
        
        #Calculate the number of actions that can possibly be taken in the game
        num_actions = model.output_shape[-1]
        
        #Dimensions of the game field
        env_dim = self.memory[0][0][0].shape[1]
        
        #We want to return an input and target vector with inputs from an observed state...
        inputs = np.zeros((min(len_memory, batch_size), env_dim))
        
        #...and the target r + gamma * max Q(s’,a’)
        #Note that our target is a matrix, with possible fields not only for the action taken but also
        #for the other possible actions. The actions not take the same value as the prediction to not affect them
        targets = np.zeros((inputs.shape[0], num_actions))
        
        #We draw states to learn from randomly
        for i, idx in enumerate(np.random.randint(0, len_memory,
                                                  size=inputs.shape[0])):
            """
            Here we load one transition <s, a, r, s’> from memory
            state_t: initial state s
            action_t: action taken a
            reward_t: reward earned r
            state_tp1: the state that followed s’
            """
            state_t, action_t, reward_t, state_tp1 = self.memory[idx][0]
            
            #We also need to know whether the game ended at this state
            game_over = self.memory[idx][1]

            #add the state s to the input
            inputs[i:i+1] = state_t
            
            # First we fill the target values with the predictions of the model.
            # They will not be affected by training (since the training loss for them is 0)
            targets[i] = model.predict(state_t)[0]
            
            """
            If the game ended, the expected reward Q(s,a) should be the final reward r.
            Otherwise the target value is r + gamma * max Q(s’,a’)
            """
            #  Here Q_sa is max_a'Q(s', a')
            Q_sa = np.max(model.predict(state_tp1)[0])
            
            #if the game ended, the reward is the final reward
            if game_over:  # if game_over is True
                targets[i, action_t] = reward_t
            else:
                # r + gamma * max Q(s’,a’)
                targets[i, action_t] = reward_t + self.discount * Q_sa
        return inputs, targets

num_actions = 3  # [move_left, stay, move_right]
hidden_size = 100 # Size of the hidden layers
grid_size = 10 # Size of the playing field

def baseline_model(grid_size,num_actions,hidden_size):
    #seting up the model with keras
    model = Sequential()
    model.add(Dense(hidden_size, input_shape=(grid_size**2,), activation='relu'))
    model.add(Dense(hidden_size, activation='relu'))
    model.add(Dense(num_actions))
    model.compile(sgd(lr=.1), "mse")
    return model

def train(model,epochs):
    # Train
    #Reseting the win counter
    win_cnt = 0
    # We want to keep track of the progress of the AI over time, so we save its win count history
    win_hist = []
    #Epochs is the number of games we play
    for e in range(epochs):
        loss = 0.
        #Resetting the game
        env.reset()
        game_over = False
        # get initial input
        input_t = env.observe()
        
        while not game_over:
            #The learner is acting on the last observed game screen
            #input_t is a vector containing representing the game screen
            input_tm1 = input_t
            
            #Take a random action with probability epsilon
            if np.random.rand() <= epsilon:
                #Eat something random from the menu
                action = np.random.randint(0, num_actions, size=1)
            else:
                #Choose yourself
                #q contains the expected rewards for the actions
                q = model.predict(input_tm1)
                #We pick the action with the highest expected reward
                action = np.argmax(q[0])

            # apply action, get rewards and new state
            input_t, reward, game_over = env.act(action)
            #If we managed to catch the fruit we add 1 to our win counter
            if reward == 1:
                win_cnt += 1        
            
            #Uncomment this to render the game here
            #display_screen(action,3000,inputs[0])
            
            """
            The experiences < s, a, r, s’ > we make during gameplay are our training data.
            Here we first save the last experience, and then load a batch of experiences to train our model
            """
            
            # store experience
            exp_replay.remember([input_tm1, action, reward, input_t], game_over)    
            
            # Load batch of experiences
            inputs, targets = exp_replay.get_batch(model, batch_size=batch_size)
  
            # train model on experiences
            batch_loss = model.train_on_batch(inputs, targets)
            
            #sum up loss over all batches in an epoch
            loss += batch_loss
        win_hist.append(win_cnt)
    return win_hist