Gym tool use environments.
Project description
Gym Tool Use
gym
tool use environments.
$ pip install gym-tool-use
Usage
import gym_tool_use # import to register gym envs
env = gym.make("TrapTube-v0")
observation = env.reset()
action = env.action_space.sample()
observation_next, reward, done, info = env.step(action)
image = env.render(mode="rgb_array") # also supports mode="human"
Environments
The following environments are registered:
"TrapTube-v0"
(base task)"PerceptualTrapTube-v0"
"StructuralTrapTube-v0"
"SymbolicTrapTube-v0"
"PerceptualSymbolicTrapTube-v0"
"StructuralSymbolicTrapTube-v0"
"PerceptualStructuralTrapTube-v0"
"PerceptualStructuralSymbolicTrapTube-v0"
Baselines
Baseline implementations here: https://github.com/fomorians/tool-use
Development
Development is started with pipenv
.
$ pipenv install
$ pipenv shell
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
gym-tool-use-1.0.0.tar.gz
(12.9 kB
view hashes)