-
Notifications
You must be signed in to change notification settings - Fork 0
Nickproger/reinforcement-NN-experiment
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
XOR: https://codepen.io/anon/pen/ERMrQq?editors=0010 World (Agent, Field(States), Actions, Rewards ...): https://codepen.io/anon/pen/XYOERp?editors=0100 https://codepen.io/anon/pen/VdNVmp?editors=0010 http://jsfiddle.net/7fzwdcy5/111/ http://jsfiddle.net/7fzwdcy5/122 http://jsfiddle.net/7fzwdcy5/685/ - positive/negative points http://jsfiddle.net/7fzwdcy5/737/ - good results http://jsfiddle.net/7fzwdcy5/888/ - strategy auto-adjusting https://jsfiddle.net/nickproger/dpcxhys0/266/ - Conv2d Layer + Dense Layer https://jsfiddle.net/nickproger/dpcxhys0/324/ https://jsfiddle.net/nickproger/dpcxhys0/328/ https://jsfiddle.net/nickproger/dpcxhys0/342/ - with `maxPooling2d` layers, works good! https://jsfiddle.net/9qdjse5u/42/ - with model output as Actions (not Q-value). Works good!
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published