Skip to main content

Gym Novel Gridworlds are environments for OpenAI Gym

Project description

Gym Novel Gridworlds

Gym Novel Gridworlds are environments for OpenAI Gym.

Installation

git clone https://github.com/gtatiya/gym-novel-gridworlds.git
cd gym-novel-gridworlds
pip install -e .

If you prefer, you can install directly from PyPI:

pip install gym-novel-gridworlds

Development Environment

Python 3.7.4 and following packages were used for development:

Python Packages

pip install gym==0.17.2
pip install keyboard==0.13.4
pip install matplotlib==3.1.2
pip install numpy==1.16.5
pip install stable_baselines=2.10.0
pip install tensorflow-gpu==1.14.0

Running

import gym
import gym_novel_gridworlds

env = gym.make('NovelGridworld-v0')

done = False
while not done:
        env.render()
        action = env.action_space.sample()
        obs, reward, done, info = env.step(action)

env.close()

Enjoy a Trained Agent

If the trained agent exists, then you can see it in action using:

python enjoy.py -env <env id> -episodes <number of episodes>

For example, enjoy PPO2 on NovelGridworld-v0 during 10 episodes:

python enjoy.py -env NovelGridworld-v0 -episodes 10

Play it yourself

Play the game using keyboard interface

cd tests
python keyboard_interface.py

Environments

NovelGridworld-v0 drawing NovelGridworld-v1 drawing
NovelGridworld-v2 drawing NovelGridworld-v3 drawing
NovelGridworld-v4 drawing NovelGridworld-v5 drawing

Project details


Download files

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

Source Distribution

gym-novel-gridworlds-1.2.tar.gz (2.0 kB view hashes)

Uploaded Source

Built Distribution

gym_novel_gridworlds-1.2-py3-none-any.whl (2.8 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page