Skip to content

MarioPPO implementation uses the TensorFlow machine learning platform

Notifications You must be signed in to change notification settings

drakyanerlanggarizkiwardhana/MarioPPO

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MarioPPO

NarrowUnselfishAmbushbug

MarioPPO stands for "Mario Proximal Policy Optimization". This is a reinforcement learning algorithm used to train artificial intelligence agents to play Super Mario Bros games automatically.

Basically, this PPO algorithm is a policy optimization technique used in context reinforcement learning. The goal is to maximize the reward or rewards that are obtained by intelligent agents in a given environment or task.

In the context of MarioPPO, the purpose of this algorithm is to optimize the policies or playing strategies of Super Mario Bros. run by intelligent agents, so that agents can obtain higher scores or achieve certain goals in the game.

Releases

No releases published

Packages

No packages published

Languages