This is an attempt to build soccer manager game using Markov Chains and Probabilistic Programming. My goal here, is to use these concepts in a pet-project just to pratice. I don't have the intention to build the next generation of Soccer Manager games, rs.
The basic idea is that players, in a determined position, have possible actions, and this actions have probabilities
For example: A player with a Foward position, should can be a something like this:
{
short_pass: 0.20,
long_pass: 0.10,
shot_on_goal: 0.70
}
The engine use this probabilities to choose what is the action that a player will do.
We need of two teams and a event listener. To start a game:
Soccer::Engine.start_game(team1, team2, event_listener)
- Fork it ( https://github.com/[my-github-username]/soccer-engine/fork )
- Create your feature branch (
git checkout -b my-new-feature
) - Commit your changes (
git commit -am 'Add some feature'
) - Push to the branch (
git push origin my-new-feature
) - Create a new Pull Request