Q-learning 比 Sarsa 更勇敢(off-policy)探索性更强,直接找 reward 最大的方向,不怕进坑里,而 Sarsa 在不断尝试中保全自身,不断少踩地雷。
Q-learning 是先用新的状态能选择的最大Q值,更新q表后选择动作,更新q表时不考虑a_
Sarsa 是在更新q表之前就选择好了动作
1、maze_env.py
import numpy as np
import time
import sys
if sys.version_info.major == 2:
import Tkinter as tk
else:
import tkinter as tk
UNIT = 40 # pixels
MAZE_H = 4 # grid height
MAZE_W = 4 # grid width
class Maze(tk.Tk, object):
def __init__(self):
super(Maze, self).__init__()
self.action_space = ['u', 'd', 'l', 'r']
self.n_actions = len(self.action_space)
self.title('maze')
self.geometry('{0}x{1}'.format(MAZE_W * UNIT, MAZE_H * UNIT))
self._build_maze()
def _build_maze(self):
self.canvas = tk.Canvas(self, bg='white',
height=MAZE_H * UNIT,
width=MAZE_W * UNIT)
# create grids
for c in range(0, MAZE_W * UNIT, UNIT):
x0, y0, x1, y1 = c, 0, c, MAZE_H * UNIT
self.canvas.create_line(x0, y0, x1, y1)
for r in range(0, MAZE_H * UNIT, UNIT):
x0, y0, x1, y1 = 0, r, MAZE_W * UNIT, r
self.canvas.create_line(x0, y0, x1, y1)
# create origin
origin = np.array([20, 20])
# hell
hell1_center = origin + np.array([UNIT * 2, UNIT])
self.hell1 = self.canvas.create_rectangle(
hell1_center[0] - 15, hell1_center[1] - 15,
hell1_center[0] + 15, hell1_center[1] + 15,
fill='black')
# hell
hell2_center = origin + np.array([UNIT, UNIT * 2])
self.hell2 = self.canvas.create_rectangle(
hell2_center[0] - 15, hell2_center[1] - 15,
hell2_center[0] + 15, hell2_center[1] + 15,
fill='black')
# create oval
oval_center = origin + UNIT * 2
self.oval = self.canvas.create_oval(
oval_center[0] - 15, oval_center[1] - 15,
oval_center[0] + 15, oval_center[1] + 15,
fill='yellow')
# create red rect
self.rect = self.canvas.create_rectangle(
origin[0] - 15, origin[1] - 15,
origin[0] + 15, origin[1] + 15,
fill='red')
# pack all
self.canvas.pack()
def reset(self):
self.update()
time.sleep(0.5)
self.canvas.delete(self.rect)
origin = np.array([20, 20])
self.rect = self.canvas.create_rectangle(
origin[0] - 15, origin[1] - 15,
origin[0] + 15, origin[1] + 15,
fill='red')
# return observation
return self.canvas.coords(self.rect)
def step1(self, action):
s = self.canvas.coords(self.rect)
base_action = np.array([0, 0])
if action == 0: # up
if s[1] > UNIT:
base_action[1] -= UNIT
elif action == 1: # down
if s[1] < (MAZE_H - 1) * UNIT:
base_action[1] += UNIT
elif action == 2: # right
if s[0] < (MAZE_W - 1) * UNIT:
base_action[0] += UNIT
elif action == 3: # left
if s[0] > UNIT:
base_action[0] -= UNIT
self.canvas.move(self.rect, base_action[0], base_action[1]) # move agent
s_ = self.canvas.coords(self.rect) # next state
# reward function
if s_ == self.canvas.coords(self.oval):
reward = 1
done = True
s_ = 'terminal'
elif s_ in [self.canvas.coords(self.hell1), self.canvas.coords(self.hell2)]:
reward = -1
done = True
s_ = 'terminal'
else:
reward = 0
done = False
return s_, reward, done
def render(self):
time.sleep(0.1)
self.update()
def update():
for t in range(10):
s = env.reset()
while True:
env.render()
a = 1
s, r, done = env.step(a)
if done:
break
if __name__ == '__main__':
env = Maze()
env.after(100, update)
env.mainloop()
2、RL_brain.py
import numpy as np
import pandas as pd
# 与 Q-learning 一样的地方,可模块化,继承
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
# 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)
# Q-learning 学习 (s, a, r, s_)
# Q - learning是先用新的状态能选择的最大 Q 值更新 q 表后选择动作,更新 q 表时不考虑 a_
# Sarsa 是在更新 q 表之前就选择好了动作
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
3、run_this.py
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
# 在循环外选 action
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.step1(action)
# RL choose action based on next observation
# Q-learning 只会估计下一个 action ,但不一定会采取
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_
# 下一步 action 是确定的
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()
4、运行结果 与Q-learning类似,但更保守,安全