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