强化学习原理入门-Day2：机器人找金币仿真环境搭建
以机器人找金币为例子，构建其MDP框架。
如图所示，网格世界中一共有8个状态，状态6和状态8是死亡区域，状态7是金币区域。机器人的初始位置为网格世界中的任意一个状态，机器人从初始状态出发寻找金币，机器人每探索一次，进入死亡区域或者找到金币，本次探索完毕。
下面将机器人建模的例子建模为MDP。
状态空间：S={1,2,3,4,5,6,7,8}；动作空间：A={东，南，西，北}；状态转移概率为机器人的运动方程，回报函数为：找到金币的回报为1，进入死亡区域的回报为-1，机器人在状态1~5之间转换时，回报为0.
下面，基于gym构建机器人找金币的gym环境。
import logging
import numpy
import random
from gym import spaces
import gym
logger = logging.getLogger(__name__)
class GridEnv(gym.Env):
metadata = {
'render.modes': ['human', 'rgb_array'],
'video.frames_per_second': 2
}
def __init__(self):
self.states = [1,2,3,4,5,6,7,8] #状态空间
self.x=[140,220,300,380,460,140,300,460]
self.y=[250,250,250,250,250,150,150,150]
self.terminate_states = dict() #终止状态为字典格式
self.terminate_states[6] = 1
self.terminate_states[7] = 1
self.terminate_states[8] = 1
self.actions = ['n','e','s','w']
self.rewards = dict(); #回报的数据结构为字典
self.rewards['1_s'] = -1.0
self.rewards['3_s'] = 1.0
self.rewards['5_s'] = -1.0
self.t = dict(); #状态转移的数据格式为字典
self.t['1_s'] = 6
self.t['1_e'] = 2
self.t['2_w'] = 1
self.t['2_e'] = 3
self.t['3_s'] = 7
self.t['3_w'] = 2
self.t['3_e'] = 4
self.t['4_w'] = 3
self.t['4_e'] = 5
self.t['5_s'] = 8
self.t['5_w'] = 4
self.gamma = 0.8 #折扣因子
self.viewer = None
self.state = None
def getTerminal(self):
return self.terminate_states
def getGamma(self):
return self.gamma
def getStates(self):
return self.states
def getAction(self):
return self.actions
def getTerminate_states(self):
return self.terminate_states
def setAction(self,s):
self.state=s
def _step(self, action):
#系统当前状态
state = self.state
if state in self.terminate_states:
return state, 0, True, {}
key = "%d_%s"%(state, action) #将状态和动作组成字典的键值
#状态转移
if key in self.t:
next_state = self.t[key]
else:
next_state = state
self.state = next_state
is_terminal = False
if next_state in self.terminate_states:
is_terminal = True
if key not in self.rewards:
r = 0.0
else:
r = self.rewards[key]
return next_state, r,is_terminal,{}
def _reset(self):
self.state = self.states[int(random.random() * len(self.states))]
return self.state
def render(self, mode='human', close=False):
if close:
if self.viewer is not None:
self.viewer.close()
self.viewer = None
return
screen_width = 600
screen_height = 400
if self.viewer is None:
from gym.envs.classic_control import rendering
self.viewer = rendering.Viewer(screen_width, screen_height)
#创建网格世界
self.line1 = rendering.Line((100,300),(500,300))
self.line2 = rendering.Line((100, 200), (500, 200))
self.line3 = rendering.Line((100, 300), (100, 100))
self.line4 = rendering.Line((180, 300), (180, 100))
self.line5 = rendering.Line((260, 300), (260, 100))
self.line6 = rendering.Line((340, 300), (340, 100))
self.line7 = rendering.Line((420, 300), (420, 100))
self.line8 = rendering.Line((500, 300), (500, 100))
self.line9 = rendering.Line((100, 100), (180, 100))
self.line10 = rendering.Line((260, 100), (340, 100))
self.line11 = rendering.Line((420, 100), (500, 100))
#创建第一个骷髅
self.kulo1 = rendering.make_circle(40)
self.circletrans = rendering.Transform(translation=(140,150))
self.kulo1.add_attr(self.circletrans)
self.kulo1.set_color(0,0,0)
#创建第二个骷髅
self.kulo2 = rendering.make_circle(40)
self.circletrans = rendering.Transform(translation=(460, 150))
self.kulo2.add_attr(self.circletrans)
self.kulo2.set_color(0, 0, 0)
#创建金条
self.gold = rendering.make_circle(40)
self.circletrans = rendering.Transform(translation=(300, 150))
self.gold.add_attr(self.circletrans)
self.gold.set_color(1, 0.9, 0)
#创建机器人
self.robot= rendering.make_circle(30)
self.robotrans = rendering.Transform()
self.robot.add_attr(self.robotrans)
self.robot.set_color(0.8, 0.6, 0.4)
self.line1.set_color(0, 0, 0)
self.line2.set_color(0, 0, 0)
self.line3.set_color(0, 0, 0)
self.line4.set_color(0, 0, 0)
self.line5.set_color(0, 0, 0)
self.line6.set_color(0, 0, 0)
self.line7.set_color(0, 0, 0)
self.line8.set_color(0, 0, 0)
self.line9.set_color(0, 0, 0)
self.line10.set_color(0, 0, 0)
self.line11.set_color(0, 0, 0)
self.viewer.add_geom(self.line1)
self.viewer.add_geom(self.line2)
self.viewer.add_geom(self.line3)
self.viewer.add_geom(self.line4)
self.viewer.add_geom(self.line5)
self.viewer.add_geom(self.line6)
self.viewer.add_geom(self.line7)
self.viewer.add_geom(self.line8)
self.viewer.add_geom(self.line9)
self.viewer.add_geom(self.line10)
self.viewer.add_geom(self.line11)
self.viewer.add_geom(self.kulo1)
self.viewer.add_geom(self.kulo2)
self.viewer.add_geom(self.gold)
self.viewer.add_geom(self.robot)
if self.state is None: return None
#self.robotrans.set_translation(self.x[self.state-1],self.y[self.state-1])
self.robotrans.set_translation(self.x[self.state-1], self.y[self.state- 1])
return self.viewer.render(return_rgb_array=mode == 'rgb_array')
注册环境：
第一步，将环境拷贝到安装目录/gym/gym/envs/classic_control文件夹中；
第二步，打开文件夹（第一步中的文件夹）下的__init__.py文件，在文件末尾加入语句：
from gym.envs.classic_control.grid_mdp import GridEnv
第三步，进入文件夹的gym安装目录/gym/gym/envs，打开该文件夹下的__init__.py文件，添加代码：
register(
id = 'GridWorld-v0',
entry_point = 'fym.envs.classic_control:GridEnv',
max_episode_steps = 200,
reward_threshold = 100.0,
)
以上三步完成了注册，下面调用该环境：
env = gym.make('GridWorld-v0')
env.reset()
env.render()
运行结果：
