A genetically evolved dinosaur that is scared of Cactus!
The game is developed using Pygame and NeuroEvolution of Augmenting Topologies (NEAT) Algorithm is the brain of the Dino.
It alters both the weighting parameters and structures of networks, attempting to find a balance between the fitness of evolved solutions and their diversity.
NEAT is based on applying three key techniques:
- Tracking genes with history markers to allow crossover among topologies
- Applying speciation (the evolution of species) to preserve innovations
- Developing topologies incrementally from simple initial structures ("complexifying").
This algorithm is so powerful that it learns the optimal policy to dodge cactus in under a minute.
The AI can take the actions of moving left, right or jump.
$ git clone https://github.com/7enTropy7/Terry_Rex.git$ pip3 install -r requirements.txt$ python3 t_rex.pyNow sit back and watch my AI play the game!
This project is licensed under the MIT License - see the LICENSE file for details