Skip to content

thorsten-j/dino-reinforcement-learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Dino reinforcement learning

This project is a little playground for reinformcement learning in games. It is inspired by Google Chrome's easter egg, the dino jump and run game.

Included is a python implementation of the game in form of an environment for reinforcement learning. An agent based on Double Deep Q-learning (DDQN) is learning to play the game. After about 1000 episodes, the agent starts to play very well (scores beyond 2000 points).

Requirements to run the game:

  • Python 3.10
  • TensorFlow >= 2.10
  • Numpy

Running the game:

python3 dino_rl.py

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages