A library for reinforcement learning environments in the field of planar robotics
Project description
Gymnasium-Planar-Robotics (GymPR)
This library contains reinforcement learning environments for motion planning and object manipulation in the field of planar robotics. The environments follow either the Gymnasium API for single-agent RL or the PettingZoo parallel API for multi-agent RL. All environments are based on the MuJoCo physics engine. Note that this library depends on the latest MuJoCo Python bindings. mujoco-py is not supported.
Installation
The Gymnasium-Planar-Robotics package can be installed via PIP:
pip install gymnasium-planar-robotics
To install optional dependencies, to build the documentation, or to run the tests, use:
pip install gymnasium-planar-robotics[docs, tests]
Note: Depending on your shell (e.g. when using Zsh), you may need to use additional quotation marks:
pip install "gymnasium-planar-robotics[docs, tests]"
Documentation
The documentation is available at: https://ubi-coro.github.io/gymnasium-planar-robotics/
License
GymPR is published under the GNU General Public License v3.0.
Example
The following example shows how to use a trained policy with an example environment that follows the Gymnasium API:
import gymnasium as gym
env = gym.make("BenchmarkPushingEnv-v0", render_mode="human")
observation, info = env.reset(seed=42)
for _ in range(0,100):
while not terminated and not truncated:
action = policy(observation) # custom policy
observation, reward, terminated, truncated, info = env.step(action)
observation, info = env.reset()
env.close()
Maintainer
Gymnasium-Planar-Robotics is currently maintained by Lara Bergmann (@lbergmann1).
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
Built Distribution
Hashes for gymnasium_planar_robotics-1.0.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 23866d8f128e8cfac75d8af19ffb88c6cf64d417e896e7dae81852d2bf96d19f |
|
MD5 | 5d790057c1116cfa17a0982b9fd11a14 |
|
BLAKE2b-256 | 3d68cf2aaac217fbce74ba39d81aebaa11970a51ca4fbb55e3e3a074674b0fdd |
Hashes for gymnasium_planar_robotics-1.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 02b2fd431ff0a89b8b22ee2ad4a45d3b817069b3310b6574456198ff0cbd6ada |
|
MD5 | c6275b58149176f1fa6a485105879505 |
|
BLAKE2b-256 | b406dbe376993b8dc0ec1d78c19811e3b49f518674ffe450a5ad7da0ec15dc5c |