莫烦强化学习：Sarsa代码学习

Q_Learning和Sarsa的算法如图所示：

对比算法可知，Q_Learning在到达状态s`后，
首先查询Q表，得到使该状态s`条件下Q值最大的动作a`，根据Q(s`, a`)计算Q现实，
随后，通过Q现实和Q估计更新Q表
在下一步执行过程中，该动作a`未必被选择

Sarsa在到达状态s`后，根据贪心策略，选择动作a`,根据Q(s`, a`)计算Q现实，
随后，通过Q现实和Q估计更新Q表
在下一步执行过程中，该动作a`需要被执行

具体代码如下：

import numpy as np
import pandas as pd


class RL(object):
    def __init__(self, action_space, learning_rate=0.01, reward_decay=0.9, 
                 e_greedy=0.9):
        self.actions = action_space  # a list
        self.lr = learning_rate
        self.gamma = reward_decay
        self.epsilon = e_greedy

        self.q_table = pd.DataFrame(columns=self.actions, dtype=np.float64)

    def check_state_exist(self, state):
        if state not in self.q_table.index:
            # append new state to q table
            self.q_table = self.q_table.append(
                pd.Series(
                    [0]*len(self.actions),
                    index=self.q_table.columns,
                    name=state,
                )
            )

    def choose_action(self, observation):
        self.check_state_exist(observation)
        # action selection
        if np.random.rand() < self.epsilon:
            # choose best action
            state_action = self.q_table.loc[observation, :]
            # some actions may have the same value, randomly choose on in these 
            # actions
            action = np.random.choice(state_action[state_action == 
                                      np.max(state_action)].index)
        else:
            # choose random action
            action = np.random.choice(self.actions)
        return action

    def learn(self, *args):
        pass


# off-policy
class QLearningTable(RL):
    def __init__(self, actions, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9):
        super(QLearningTable, self).__init__(actions, learning_rate, reward_decay, 
                                             e_greedy)

    def learn(self, s, a, r, s_):
        self.check_state_exist(s_)
        q_predict = self.q_table.loc[s, a]
        if s_ != 'terminal':
            q_target = r + self.gamma * self.q_table.loc[s_, :].max()  
             # next state is not terminal
        else:
            q_target = r  # next state is terminal
        self.q_table.loc[s, a] += self.lr * (q_target - q_predict)  # update


# on-policy
class SarsaTable(RL):

    def __init__(self, actions, learning_rate=0.01, reward_decay=0.9, e_greedy=0.9):
        super(SarsaTable, self).__init__(actions, learning_rate, reward_decay, 
              e_greedy)

    def learn(self, s, a, r, s_, a_):
        self.check_state_exist(s_)
        q_predict = self.q_table.loc[s, a]
        if s_ != 'terminal':
            q_target = r + self.gamma * self.q_table.loc[s_, a_]  
            # next state is not terminal
        else:
            q_target = r  # next state is terminal
        self.q_table.loc[s, a] += self.lr * (q_target - q_predict)  # update

 

from maze_env import Maze
from RL_brain import SarsaTable


def update():
    for episode in range(100):
        # initial observation
        observation = env.reset()

        # RL choose action based on observation
        action = RL.choose_action(str(observation))

        while True:
            # fresh env
            env.render()

            # RL take action and get next observation and reward
            observation_, reward, done = env.step(action)

            # RL choose action based on next observation
            action_ = RL.choose_action(str(observation_))

            # RL learn from this transition (s, a, r, s, a) ==> Sarsa
            RL.learn(str(observation), action, reward, str(observation_), action_)

            # swap observation and action
            observation = observation_
            action = action_

            # break while loop when end of this episode
            if done:
                break

    # end of game
    print('game over')
    env.destroy()

if __name__ == "__main__":
    env = Maze()
    RL = SarsaTable(actions=list(range(env.n_actions)))

    env.after(100, update)
    env.mainloop()