Skip to content

sgoad13/a2ReinforcementLearning

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 

Repository files navigation

a2ReinforcementLearning

Bryan Truong, Shannon Goad

COMP560 A2: Reinforcement Learning for 3d Tic Tac Toe with NumPy and python3. You must have NumPy and Python 3.6 or greater to run the program. Clone Directory and run from the shell in the root project directory by calling python3 learn4x4x4.py x y z, where x, y, and z are non-negative, increasing integers that represent the number of trials to run.

Example run command: python3 learn4x4x4.py 100 500 2000

The program will then print the current utility values after x trials, y trials, then z trials. The link to our full project write-up is here.

About

COMP560 A2: Reinforcement Learning for 3d Tic Tac Toe

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%