强化学习Sarsa算法实践

公式

练习背景

寻路游戏，学习到达终点而不掉进黑框的可行路径（但是不一定是最短可行路径）。

源码路径：百度PARL包，examples\tutorials\lesson2\sarsa

源码分析

包含三个文件：gridworld.py、agent.py、train.py

GRIDWORLD

提供寻路游戏的虚拟环境Environment，封装了State、Action、Reward和可视化界面，略。

AGENT

① 根据Q表格选动作

class SarsaAgent(object):
    def __init__(self,
                 obs_n,
                 act_n,
                 learning_rate=0.01,
                 gamma=0.9,
                 e_greed=0.1):
        self.act_n = act_n  # 动作维度，有几个动作可选
        self.lr = learning_rate  # 学习率
        self.gamma = gamma  # reward的衰减率
        self.epsilon = e_greed  # 按一定概率随机选动作
        self.Q = np.zeros((obs_n, act_n))

    # 根据输入观察值，采样输出的动作值，带探索
    def sample(self, obs):
        if np.random.uniform(0, 1) < (1.0 - self.epsilon):  #根据table的Q值选动作
            action = self.predict(obs)
        else:
            action = np.random.choice(self.act_n)  #有一定概率随机探索选取一个动作
        return action

    # 根据输入观察值，预测输出的动作值
    def predict(self, obs):
        Q_list = self.Q[obs, :]
        maxQ = np.max(Q_list)
        action_list = np.where(Q_list == maxQ)[0]  # maxQ可能对应多个action
        action = np.random.choice(action_list)
        return action

② 更新Q表格

    # 学习方法，也就是更新Q-table的方法
    def learn(self, obs, action, reward, next_obs, next_action, done):
        """ on-policy
            obs: 交互前的obs, s_t
            action: 本次交互选择的action, a_t
            reward: 本次动作获得的奖励r
            next_obs: 本次交互后的obs, s_t+1
            next_action: 根据当前Q表格, 针对next_obs会选择的动作, a_t+1
            done: episode是否结束
        """
        predict_Q = self.Q[obs, action]
        if done:
            target_Q = reward  # 没有下一个状态了
        else:
            target_Q = reward + self.gamma * self.Q[next_obs,
                                                    next_action]  # Sarsa
        self.Q[obs, action] += self.lr * (target_Q - predict_Q)  # 修正q

Train

运行的代码

def main():
    # env = gym.make("FrozenLake-v0", is_slippery=False)  # 0 left, 1 down, 2 right, 3 up
    # env = FrozenLakeWapper(env)

    env = gym.make("CliffWalking-v0")  # 0 up, 1 right, 2 down, 3 left
    env = CliffWalkingWapper(env)

    agent = SarsaAgent(
        obs_n=env.observation_space.n,
        act_n=env.action_space.n,
        learning_rate=0.1,
        gamma=0.9,
        e_greed=0.1)

    is_render = False
    for episode in range(500):
        ep_reward, ep_steps = run_episode(env, agent, is_render)
        print('Episode %s: steps = %s , reward = %.1f' % (episode, ep_steps,
                                                          ep_reward))

        # 每隔20个episode渲染一下看看效果
        if episode % 20 == 0:
            is_render = True
        else:
            is_render = False
    # 训练结束，查看算法效果
    test_episode(env, agent)

模块代码

def run_episode(env, agent, render=False):
    total_steps = 0  # 记录每个episode走了多少step
    total_reward = 0

    obs = env.reset()  # 重置环境, 重新开一局（即开始新的一个episode）
    action = agent.sample(obs)  # 根据算法选择一个动作

    while True:
        next_obs, reward, done, _ = env.step(action)  # 与环境进行一个交互
        next_action = agent.sample(next_obs)  # 根据算法选择一个动作
        # 训练 Sarsa 算法
        agent.learn(obs, action, reward, next_obs, next_action, done)

        action = next_action
        obs = next_obs  # 存储上一个观察值
        total_reward += reward
        total_steps += 1  # 计算step数
        if render:
            env.render()  #渲染新的一帧图形
        if done:
            break
    return total_reward, total_steps


def test_episode(env, agent):
    total_reward = 0
    obs = env.reset()
    while True:
        action = agent.predict(obs)  # greedy
        next_obs, reward, done, _ = env.step(action)
        total_reward += reward
        obs = next_obs
        time.sleep(0.5)
        env.render()
        if done:
            print('test reward = %.1f' % (total_reward))
            break