Skip to content

A python templates for starters to practice on - train your Reinforcement learning algorithm on this template

License

Notifications You must be signed in to change notification settings

avivgood/Reinforcement-learning-starters-template

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Reinforcement-learning-starters-template

A python stragedy game in which the programer will create a python reinforcement learning algorithem (that will play againt itself or against the algorithem provided in the project or even against a player) in order to beat the game and make the best algortithm.

#Basic game rules:

-there are 3 players - blue, red, and gray

-the gray player is not represented by an algorithem nor a player - he does not move or do any action. he merely holds level 2 towers that has 10 inital warriors between the towers of the red and blue team

-the Blue and red players start with level 1 towers (exact layout and conditions may very from configaration to configaration) and 5 inital warriors with a goal of taking all the towers of the other player

-towers can hold warriors

-a road connects towers togther

-warriors can be sent to other towers using roads in the 2 events specified below. time traveling from tower to tower may vary from road to road

-a player can send warriors to a tower of his own to supply it with more warriors

-a player can attack a tower which is not his. When attacking a tower the attacker and tower forces cancle out in a 1:1 ratio. If the tower is overwalmed with opponent warriors he is captured by the opponent

-towers yhilds number of warriors per turn, depends on the level of the tower

-a tower can be upgraded in a cost of warriors. upgrades takes few turns to finish in which no warriors are created

-the game is won when all the towers of the oponents are taken

About

A python templates for starters to practice on - train your Reinforcement learning algorithm on this template

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages