# Deep-Reinforcement-Learning-for-Solving-Job-Shop-Scheduling-Problems
*In the past decades, many optimization methods have been devised and applied to
job shop scheduling problem (JSSP) to find the optimal solution. Most methods assume
that the scheduling results are applied to static environments. However, the whole
environments in the real word are always dynamic and many unexpected events make
original solutions to fail.*
*In this essay, we view JSSP as a sequential decision making
problem and propose to use deep reinforcement learning model to tackle this problem.
Th e combination of deep learning and reinforcement learning avoids to handcraft
features as used in traditional reinforcement learning, and it is expected that the
combination will make the whole learning phase more efficient. Our proposed model
consists of actor network and critic network, and both networks include convolution
layers and fully connected layer. Ac tor network let agent learn how to behave in
different situations, while critic network help agent evaluate the value of statement t hen
return to ac tor network. The whole network is trained with parallel training on a multi
agent environment a nd different simple dispatching rules are considered as actions.*
*We evaluate our proposed model on more than ten instances that are present in a famous
benchmark problem library OR library. The evaluation results indicate that no matter
in static JSSP benchmark problem or in stochastic JSSP, our method can compete with
other alternatives.*
---
<img src="IMG/QQ.jpg" width = "350" height = "300" alt="图片名称" align=center /> <img src="IMG/ASY.jpg" width = "350" height = "300" alt="图片名称" align=center />
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
Deep-Reinforcement-Learning-for-Solving-Job-Shop-Scheduling-Problems-master.zip (46个子文件)
Deep-Reinforcement-Learning-for-Solving-Job-Shop-Scheduling-Problems-master
exp
exp105.py 8KB
exp155.py 8KB
exp205.py 9KB
exp1010.py 10KB
exp55.py 10KB
exp66.py 9KB
IMG
ASY.jpg 41KB
QQ.jpg 47KB
README.md 2KB
utils
pic.py 734B
pre.py 8KB
shared_adam.py 794B
job.py 7KB
utils.py 2KB
la02.py 5KB
testnet.py 2KB
DRL
net1010.py 2KB
net205.py 2KB
1 1B
net155.py 2KB
net105.py 2KB
net2015.py 2KB
net66.py 3KB
net55.py 2KB
instance
la11.txt 518B
ft10.txt 508B
orb09.txt 508B
abz7.txt 2KB
orb02.txt 508B
orb06.txt 508B
la02.txt 261B
ft06.txt 215B
orb08.txt 508B
la15.txt 518B
orb04.txt 508B
orb03.txt 508B
la06.txt 388B
la12.txt 518B
la13.txt 518B
orb05.txt 508B
orb10.txt 508B
abz8.txt 2KB
orb07.txt 508B
orb01.txt 508B
abz9.txt 2KB
la14.txt 518B
共 46 条
- 1
码丽莲梦露
- 粉丝: 7350
- 资源: 16
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
- 1
- 2
- 3
- 4
- 5
- 6
前往页