Skip to main content

Reinforcement Learning Environments for train RL agents

Project description

TEG

TEG is a straightforward environment for Reinforcement Learning that enables the training of RL agents for a robot manipulator. It's based on the Gymnasium and Mujoco.

Installation

This project use python 3.7+

You can install it by using pip

pip install TEG

Or manually cloning the github repository

git clone https://github.com/Alexfm101/TEG.git 
cd TEG
python -m pip install -e .

Example

TEG environment are simple Python env classes to allow an AI agent to interact with them very simple. Here's an example:

from TEG.envs.UR5_v0 import UR5Env_v0

env = UR5Env_v0(simulation_frames=5, torque_control= 0.01, distance_threshold=0.05)

def main():
    for episode in range(5):
        print("episode {}".format(episode))
        env.reset()

        for t in range(1000):
            action = env.action_space.sample()
            observation, reward, done, info = env.step(action)
            
            
            if done:
                print("Episode finished after {} timesteps".format(t+1))
                break

    return env.robot, env.sim

if __name__ == '__main__':
    main()

🧾 License

The Apache 2.0 License

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

TEG-1.0.0rc1.tar.gz (8.9 kB view details)

Uploaded Source

Built Distribution

TEG-1.0.0rc1-py3-none-any.whl (9.4 kB view details)

Uploaded Python 3

File details

Details for the file TEG-1.0.0rc1.tar.gz.

File metadata

  • Download URL: TEG-1.0.0rc1.tar.gz
  • Upload date:
  • Size: 8.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.12

File hashes

Hashes for TEG-1.0.0rc1.tar.gz
Algorithm Hash digest
SHA256 e40b9e0d93dacafed2234731330e367389d734e38ad408d5033e3b29d35f8a3d
MD5 67172ea048ae0d30d0caaa18aeb107b4
BLAKE2b-256 47a91a038bef19c47fd050d9b77e3b13c2aa627d9ac8cd866f45b35d48b2fa39

See more details on using hashes here.

File details

Details for the file TEG-1.0.0rc1-py3-none-any.whl.

File metadata

  • Download URL: TEG-1.0.0rc1-py3-none-any.whl
  • Upload date:
  • Size: 9.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.12

File hashes

Hashes for TEG-1.0.0rc1-py3-none-any.whl
Algorithm Hash digest
SHA256 825b5a1bc308eca933bf1ffbbaa07ba0d901ae7f17bc86531070ab3903383c90
MD5 6e5b23ca6fc6a593bc7fc231f37af53b
BLAKE2b-256 791db386ae88c4365e6c5a5a326c459df5ac719d21e49c748f0d9b4c69277341

See more details on using hashes here.

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