Skip to main content
Join the official 2020 Python Developers SurveyStart the survey!

A simple 2D maze environment for OpenAI Gym

Project description

gym-maze

A simple 2d maze environment for Open AI Gym, where the agent needs to finds its way from the top left corner to the bottom right corner.

Action space

The agent may only choose to go up, down, left, or right ("N", "S", "W", "E"). If the way is blocked, it will remain at the same the location.

Observation space

The observation space is the (x, y) coordinate of the agent. The top left cell is (0, 0).

Reward

A reward of 1 is given when the agent reaches the goal. For every step in the maze, the agent recieves a reward of -0.1/(number of cells).

End condition

The maze is reset when the agent reaches the goal.

Maze Versions

Pre-generated mazes

  • 5 cells x 5 cells: MazeEnvSample5x5
  • 10 cells x 10 cells: MazeEnvSample10x10
  • 25 cells x 25 cells: MazeEnvSample25x25
  • 50 cells x 50 cells: MazeEnvSample50x50
  • 100 cells x 100 cells: MazeEnvSample100x100

Randomly generated mazes

  • 5 cells x 5 cells: MazeEnvRandom5x5
  • 10 cells x 10 cells: MazeEnvRandom10x10
  • 25 cells x 25 cells: MazeEnvRandom25x25
  • 50 cells x 50 cells: MazeEnvRandom50x50
  • 100 cells x 100 cells: MazeEnvRandom100x100

Requirements

You need Python 3.6 or 3.7 to run the script. After this, install the package.

  • python setup.py install

Another way to install the package is by using test.pypi.org.

  • pip install gym-maze-trustycoder83

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for gym-maze-trustycoder83, version 0.0.4
Filename, size File type Python version Upload date Hashes
Filename, size gym_maze_trustycoder83-0.0.4-py2.py3-none-any.whl (18.2 kB) File type Wheel Python version py2.py3 Upload date Hashes View
Filename, size gym-maze-trustycoder83-0.0.4.tar.gz (23.7 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page