Skip to content

2017-fall-DL-training-program/Reinforcement_Learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Detials for Lab 4

├─ LAB4_slide  [Slide for quick overview]
├─ LAB4_spec   [Specification for Lab 4] 
└─ Q-learning   
     ├─ Q_Learning_Demo.pptx    [Detials for DQN]
     └─ q_learning_demo.cpp     [Q learning toy demo]

Use an Remote Desktop Application to connect to your machine

Run your code for training

IMAGE ALT TEXT

Remember to save testing log

  • In this training, you will get 64.725 point

  • Test plot like this:

You may try anthor training (if your algorithm is right but ) or modify your code.

  • In this training, you will get 100 point

  • Test plot like this:

That is what you want to see.

Remember to save training vedios

MONITOR_PATH        = './vedio'       # video path
RECORD_VIDEO_FLAG   = True            # record video or not

IMAGE ALT TEXT

About

MTK Deep Learning (RL part)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages