问题描述
我正在尝试使用 simpy 模块 (https://simpy.readthedocs.io/en/latest/index.html) 编程和模拟作业车间问题。最后我想用强化学习来优化这个问题。但是，我的问题是当我尝试模拟创建的序列（尚未由代理生成）时，simpy 对所有资源（机器）使用时间。我曾想过将带有while循环的各个操作传递给simpy的超时事件，然后进行模拟。但是，它不起作用。有人能帮我吗？到目前为止，这是我的代码。
15 15
6 94 12 66 4 10 7 53 3 26 2 15 10 65 11 82 8 10 14 27 9 93 13 92 5 96 0 70 1 83
4 74 5 31 7 88 14 51 13 57 8 78 11 8 9 7 6 91 10 79 0 18 3 51 12 18 1 99 2 33
1 4 8 82 9 40 12 86 6 50 11 54 13 21 5 6 0 54 2 68 7 82 10 20 4 39 3 35 14 68
5 73 2 23 9 30 6 30 10 53 0 94 13 58 4 93 7 32 14 91 11 30 8 56 12 27 1 92 3 9
7 78 8 23 6 21 10 60 4 36 9 29 2 95 14 99 12 79 5 76 1 93 13 42 11 52 0 42 3 96
5 29 3 61 12 88 13 70 11 16 4 31 14 65 7 83 2 78 1 26 10 50 0 87 9 62 6 14 8 30
12 18 3 75 7 20 8 4 14 91 6 68 1 19 11 54 4 85 5 73 2 43 10 24 0 37 13 87 9 66
11 32 5 52 0 9 7 49 12 61 13 35 14 99 1 62 2 6 8 62 4 7 3 80 9 3 6 57 10 7
10 85 11 30 6 96 14 91 0 13 1 87 2 82 5 83 12 78 4 56 8 85 7 8 9 66 13 88 3 15
6 5 11 59 9 30 2 60 8 41 0 17 13 66 3 89 10 78 7 88 1 69 12 45 14 82 4 6 5 13
4 90 7 27 13 1 0 8 5 91 12 80 6 89 8 49 14 32 10 28 3 90 1 93 11 6 9 35 2 73
2 47 14 43 0 75 12 8 6 51 10 3 7 84 5 34 8 28 9 60 13 69 1 45 3 67 11 58 4 87
5 65 8 62 10 97 2 20 3 31 6 33 9 33 0 77 13 50 4 80 1 48 11 90 12 75 7 96 14 44
8 28 14 21 4 51 13 75 5 17 6 89 9 59 1 56 12 63 7 18 11 17 10 30 3 16 2 7 0 35
10 57 8 16 12 42 6 34 4 37 1 26 13 68 14 73 11 5 0 8 7 12 3 87 2 83 9 20 5 97
import gym
import simpy
from simpy.events import AnyOf,AllOf,Event
import random
import numpy as np
class JobShop_RL(gym.Env):
def __init__(self):
# Reading the Dataset for the JSP
with open("taillard.txt","r") as self.data:
self.read_data = self.data.readline()
self.line = self.read_data.split()
# Getting number of Jobs and Machines
self.jobs = int(self.line[0])
self.machines = int(self.line[1])
self.all_jobs = np.zeros((self.jobs,self.machines),dtype=(int,2))
# Filling Matrix with (jobs/number) = (machine/time)
self.line = self.data.readline()
job = 0
self.max_time = 0 # Max time
self.sum_time = 0 # Sum of the whole time
self.jobs_duration = np.zeros(self.machines,dtype=int) # Sum of time for each job
i = 0
j = 0
while job < self.jobs:
self.line = self.line.split()
while i <= ((self.jobs + self.machines) - 1):
self.all_jobs[job][j] = int(self.line[i]),int(self.line[i + 1])
self.jobs_duration[job] += int(self.line[i + 1])
self.max_time = max(self.max_time,int(self.line[i + 1]))
self.sum_time += int(self.line[i + 1])
j += 1
i += 2
self.line = self.data.readline()
job += 1
i = 0
j = 0
# possible legal actions + the same number for no op for each machine
# e. g. 15x15 Jssp = 15 legal moves and also 15 no op
self.action_space = gym.spaces.discrete(self.machines+self.machines)
# observation space
self.observation_space = gym.spaces.Box
# jobs_done = last stage,storing all jobs which are done
self.jobs_done = []
# last jobs = represents jobs the last jobs ( = nb of machines) which are done
#self.last_jobs = np.zeros(self.jobs,2))
# last jobs = represents jobs the last jobs ( = nb of machines) which are done
self.possible_actions = np.zeros(self.jobs,2))
i = 0
while i < self.machines:
self.possible_actions[i] = self.all_jobs[i][0]
i += 1
#
self.counting = np.zeros(self.machines)
# final order of the job shop problem
self.final_order = np.zeros_like(self.all_jobs)
self.simpy_env = simpy.Environment()
# Store the simpy resources (machines) in the list
self.machines_sy = []
i = 0
while i <= self.machines:
self.machines_sy.append(simpy.Resource(self.simpy_env,capacity=1))
i += 1
def get_operation_index(self,action):
index_machine = action // self.jobs
index_operation = action % self.jobs
#print("INDEX",index_operation,index_machine,self.all_jobs[index_operation][index_machine])
# Returns the Indizes of the action,[Machine][Operation]
return index_operation,index_machine
def get_machine(self,action):
nb_machine = self.all_jobs[self.get_operation_index(action)]
return nb_machine[0]
def machine_process(self,simpy_env,action):
#Request and timeout the action for each incoming action (if machine is busy its going in the queue)
machine = self.get_machine(action)
print("ACTION IN MACHINE PROCESS",action)
#operation = self.possible_actions[action]
#operation = self.final_order[machine][int(self.counting[action])]
#print("OPERATION",operation)
i = 0
j = 0
while i < self.machines:
while j < self.jobs:
operation = self.final_order[i][j]
with self.machines_sy[operation[0]].request() as req:
yield req
print("Machine ",i," proceed Operation ",self.final_order[i][j]," at ",simpy_env.Now)
self.jobs_done.append(self.final_order[machine][int(self.counting[action])])
yield simpy_env.timeout(operation[1]) # Operation[1] defines the processing time
print("Machine "," released Operation ",simpy_env.Now)
j += 1
if j == 15:
i += 1
j = 0
def is_done(self):
# Returns True if len(jobs_done) is the same as the sum of operations which need to be done
# ### Die Anzahl an no ops muss beachtet werden
if len(self.jobs_done) == self.all_jobs.shape[1]*self.all_jobs.shape[0]:
return True
else:
return False
def take_action(self,action):
nb_machine = self.possible_actions[action]
nb_machine = nb_machine[0]
self.simpy_env.process(env.machine_process(env.simpy_env,action))
machine = self.get_machine(action)
# Filling Final Order
tmp = np.count_nonzero(self.final_order[nb_machine]) // 2
self.final_order[nb_machine][tmp] = self.possible_actions[action]
# Update possible actions
self.possible_action(action)
def possible_action(self,action):
self.counting[action] += 1
self.possible_actions[action] = self.all_jobs[action][int(self.counting[action])]
def step(self,action):
reward = 0
operation = self.get_operation_index(action)
if action <= self.machines:
print("##STEP## norMALE ACTION",action,self.possible_actions[action])
self.take_action(action)
reward = 10
elif self.machines < action <= self.action_space.n:
print("NOOP",action)
reward = -3
#Check if done
done = self.is_done()
#Info is unused
info = {}
return reward,done,info
def reset(self):
pass
def render(self,mode='human'):
pass
if __name__ == "__main__":
env = JobShop_RL()
print(env.possible_actions)
env.step(0)
print("****## NEXT ##***")
env.step(1)
print("****## NEXT ##***")
env.step(2)
print("****## NEXT ##***")
env.simpy_env.run(1000)
解决方法
暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！
如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。
小编邮箱:dio#foxmail.com (将#修改为@）