https://github.com/vivek3141/snake-gym

A gym environment for the game snake, with a tiled version. Contains implementations for NEAT and RL.
https://github.com/vivek3141/snake-gym

deep-q-network dopamine dopamine-rl reinforcement-learning snake snake-ai

Last synced: 2 months ago
JSON representation

A gym environment for the game snake, with a tiled version. Contains implementations for NEAT and RL.

• Host: GitHub
• URL: https://github.com/vivek3141/snake-gym
• Owner: vivek3141
• License: mit
• Created: 2018-09-09T07:18:37.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2020-03-30T22:14:37.000Z (about 5 years ago)
• Last Synced: 2024-10-03T01:43:25.964Z (8 months ago)
• Topics: deep-q-network, dopamine, dopamine-rl, reinforcement-learning, snake, snake-ai
• Language: Python
• Homepage: https://pypi.org/project/snake-gym/
• Size: 793 KB
• Stars: 9
• Watchers: 3
• Forks: 3
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# Snake-Gym

[![Downloads](https://pepy.tech/badge/snake-gym)](https://pepy.tech/project/snake-gym)

[![PyPi Version](https://img.shields.io/pypi/v/snake-gym.svg)](https://pypi.python.org/pypi/snake-gym)

[![Python Compatibility](https://img.shields.io/pypi/pyversions/snake-gym.svg)](https://pypi.python.org/pypi/snake-gym)

[![License](https://img.shields.io/pypi/l/snake-gym.svg)](https://pypi.python.org/pypi/snake-gym)


Contains a gym environment for the classic game snake.

## Implementing

* `env.render()` is not implemented, running it will raise `NotImplementedError`.

* `env.reset()` opens the GUI for the game. 

* `env.fps` contains the fps to run the game at. You can set it using:

    ```python

    env.fps = 60

    ```

## Installation

For the latest installation, run

```bash

git clone https://github.com/vivek3141/snake-gym

pip install -e .

```

You can install the latest release by

```bash

pip install snake-gym

```

## Creating The Environment

The environment can be created by doing the following:

```python

import gym

import snake_gym

env = gym.make("snake-v0")

```

## Environments

* `snake-v0` Returns a 150x150 RGB image in the form of a numpy array for the observations

* `snake-tiled-v0` Returns a 10x10 matrix for the observations. 

    * `0` is empty space

    * `1` is the snake

    * `2` is the food