An OpenAI Gym interface for the AI safety gridworlds by DeepMind, which are implemented in pycolab.
This repository combines and extends two previous implementations which can be found at:
safe_grid_gym
additionally provides:
ansi
and rgb_array
allowing for more automated experimentationTransitionBoatRace
environments which provides the last two boards as state informationsetup.py
ai-safety-gridworlds
repositoryTo handle the dependency on the ai-safety-gridworlds
we use a fork of the official repository that provides a setup.py
.
You can use the code from the official ai-safety-gridworlds
repository instead by adding it to your PYTHONPATH
.
By using safe_grid_gym
the AI safety gridworlds can by used like any other gym environment. For example to take 10 random actions in the boat race environment and render the gridworld, you can do:
import safe_grid_gym
import gym
env = gym.make("BoatRace-v0")
action_space = env.action_space
for i in range(10):
action = action_space.sample()
state, reward, done, info = env.step(action)
env.render(mode="human")