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
Introduction to
Deep Reinforcement
Learning
2019
https://deeplearning.mit.edu
For the full list of references visit:
https://hcai.mit.edu/references
Deep Reinforcement Learning (Deep RL)
• What is it? Framework for learning to solve sequential decision
making problems.
• How? Trial and error in a world that provides occasional rewards
• Deep? Deep RL = RL + Neural Networks
[306, 307]
Deep Learning Deep RL
2019
https://deeplearning.mit.edu
Types of Learning
• Supervised Learning
• Semi-Supervised Learning
• Unsupervised Learning
• Reinforcement Learning
It’s all “supervised” by a loss function!
*Someone has to say what’s good and what’s bad (see Socrates, Epictetus, Kant, Nietzsche, etc.)
Neural
Network
Input Output
Good or
Bad?
Supervision*
2019
https://deeplearning.mit.edu
For the full list of references visit:
https://hcai.mit.edu/references
Supervised learning is “teach by example”:
Here’s some examples, now learn patterns in these example.
Reinforcement learning is “teach by experience”:
Here’s a world, now learn patterns by exploring it.
2019
https://deeplearning.mit.edu
For the full list of references visit:
https://hcai.mit.edu/references
Machine Learning:
Supervised vs Reinforcement
Supervised learning is “teach by example”:
Here’s some examples, now learn patterns in these example.
Reinforcement learning is “teach by experience”:
Here’s a world, now learn patterns by exploring it.
[330]
Failure Success
剩余75页未读,继续阅读
资源评论
passionSnail
- 粉丝: 448
- 资源: 6875
下载权益
C知道特权
VIP文章
课程特权
开通VIP
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
最新资源
- libncursesso5、lib、依赖包
- 使用Bootload升级相关的开发笔记
- c++调用windowns SDK设置默认的输出音频设备
- 802.3df-2024
- 毕业设计 基于深度学习YOLOX+DeepSORT的多目标跟踪系统源码+运行教程.zip
- 西安电子科技大学2024年a测湿度监测系统实验GUI界面python代码,python环境可以直接运行,无需调试
- 期末复习必备-保姆级别,两小时解决python基础知识(附代码版本)
- Simulink加速单踏板驾驶特性开发
- 暴风电视刷机 55X4 ECHO 屏LC550EGY-SJM2 机编60000AM8001 屏参30173001 V1.0.35
- c++控制屏幕克隆dll
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
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