Snake Machine Learning Implementation

Snake-AI

Observation

Visual observation

• Visual observation. The AI is observing a 13x13 space around this head. Six on the left and right site and the Head in the middle.

Static observation

• Raytracing along the yellow dashed lines. The AI is able to see himself, walls and the apple.
• Direction (red line) of the snake.
• apple (blue point) and tail compass. Indicates the relativ position according to the apple or the last part of the snake.
• step counter. If the snake doesn't eat an apple in a descried amount of steps the game ends.

Evaluation / Reward

+100 if the snake reaches the max length. | win

+2.5 if snake eats an apple.

-10 if the snake dies. | loss

Implementation

The current built was inspired by:
Phil Tabor: Phil Tabor - Repository
Nikhil Barhate: nikhilbarhate99 - Repository

References

• PPO paper
• DQN paper

Instructions

License

GPLv3 (General Public License 3)

Results

Dependencies

Libraries           | Functions
-----------------------------------------------
...                 | ...
python 3.7          | Python version
gym 0.21.0          | Game setup
pygame 2.0.2        | Game gui
numpy 1.21.2        | Creating observations
Pytorch 1.9.1 cuda  | Machine Learning API
scipy 1.7.1         | Linear regression
matplotlib 3.4.3    | Result plots
pandas 1.3.3        | Hadling the generated data
pathlib 1.0.1       | Hadling the paths