深度学习总结：DQN原理，算法及pytorch方式实现

Q-learning原理图

Q-learning算法描述：

pytorch实现：

Q-network实现：

输入s，输出是Q(s,a_i)即所有action在s下对应的Q值。

class Net(nn.Module):
    def __init__(self, ):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(N_STATES, 50)
        self.fc1.weight.data.normal_(0, 0.1)   # initialization
        self.out = nn.Linear(50, N_ACTIONS)
        self.out.weight.data.normal_(0, 0.1)   # initialization

    def forward(self, x):
        x = self.fc1(x)
        x = F.relu(x)
        actions_value = self.out(x)
        return actions_value

DQN实现：

DQN包含：

2个Q-network，其中一个为target Q-network；

class DQN(object):
    def __init__(self):
        self.eval_net, self.target_net = Net(), Net()

        self.learn_step_counter = 0                                     # for target updating
        self.memory_counter = 0                                         # for storing memory
        self.memory = np.zeros((MEMORY_CAPACITY, N_STATES * 2 + 2))     # initialize memory
        self.optimizer = torch.optim.Adam(self.eval_net.parameters(), lr=LR)
        self.loss_func = nn.MSELoss()

take action获取下一步的动作，这个部分就是和环境互动的部分，选取动作是基于e-greedy来的；

    def choose_action(self, x):
        x = torch.unsqueeze(torch.FloatTensor(x), 0)
        # input only one sample
        if np.random.uniform() < EPSILON:   # greedy
            actions_value = self.eval_net.forward(x)
            action = torch.max(actions_value, 1)[1].data.numpy()
            action = action[0] if ENV_A_SHAPE == 0 else action.reshape(ENV_A_SHAPE)  # return the argmax index
        else:   # random
            action = np.random.randint(0, N_ACTIONS)
            action = action if ENV_A_SHAPE == 0 else action.reshape(ENV_A_SHAPE)
        return action

store transmitions就是保存数据，用于experience replay；

    def store_transition(self, s, a, r, s_):
        transition = np.hstack((s, [a, r], s_))
        # replace the old memory with new memory
        index = self.memory_counter % MEMORY_CAPACITY
        self.memory[index, :] = transition
        self.memory_counter += 1

最重要的是学习过程：就是算法描述的核心部分, 需要针对minibatach的处理，需要做regression更新Q-network，还需要定期更新target Q-network。

    def learn(self):
        # target parameter update
        if self.learn_step_counter % TARGET_REPLACE_ITER == 0:
            self.target_net.load_state_dict(self.eval_net.state_dict())
        self.learn_step_counter += 1

        # sample batch transitions
        sample_index = np.random.choice(MEMORY_CAPACITY, BATCH_SIZE)
        b_memory = self.memory[sample_index, :]
        b_s = torch.FloatTensor(b_memory[:, :N_STATES])
        b_a = torch.LongTensor(b_memory[:, N_STATES:N_STATES+1].astype(int))
        b_r = torch.FloatTensor(b_memory[:, N_STATES+1:N_STATES+2])
        b_s_ = torch.FloatTensor(b_memory[:, -N_STATES:])

        # q_eval w.r.t the action in experience
        q_eval = self.eval_net(b_s).gather(1, b_a)  # shape (batch, 1)
        q_next = self.target_net(b_s_).detach()     # detach from graph, don't backpropagate
        q_target = b_r + GAMMA * q_next.max(1)[0].view(BATCH_SIZE, 1)   # shape (batch, 1)
        loss = self.loss_func(q_eval, q_target)

        self.optimizer.zero_grad()
        loss.backward()
        self.optimizer.step()

训练实现：优化游戏环境的reward, 实现算法描述的for each episode(通过for range控制) for each time step（通过游戏返回的done终止）

dqn = DQN()

print('\nCollecting experience...')
for i_episode in range(400):
    s = env.reset()
    ep_r = 0
    while True:
        env.render()
        a = dqn.choose_action(s)

        # take action
        s_, r, done, info = env.step(a)

        # modify the reward
        x, x_dot, theta, theta_dot = s_
        r1 = (env.x_threshold - abs(x)) / env.x_threshold - 0.8
        r2 = (env.theta_threshold_radians - abs(theta)) / env.theta_threshold_radians - 0.5
        r = r1 + r2

        dqn.store_transition(s, a, r, s_)

        ep_r += r
        if dqn.memory_counter > MEMORY_CAPACITY:
            dqn.learn()
            if done:
                print('Ep: ', i_episode,
                      '| Ep_r: ', round(ep_r, 2))

        if done:
            break
        s = s_