OpenAI Gym environment designed for training RL agents to balance double CartPole.
Project description
This package contains OpenAI Gym environment designed for training RL agents to balance double CartPole. The environment is automatically registered under id: double-cartpole-custom-v0, so it can be easily used by RL agent training libraries, such as StableBaselines3.
At the https://github.com/mareo1208/Double-cartpole-custom-gym-env-for-reinforcement-learning.git you can find a detailed description of the environment, along with a description of the package installation and sample code made to train and evaluate agents in this environment. Additionally, there is code showing how to use the library StableBaselines3 and Optuna to search for the best hyperparameters. All examples are available in two versions: as a script ready to run on your computer and as a script ready to run in the Google Colab service.
This environment was created for the needs of my bachelor's thesis, available at https://www.ap.uj.edu.pl/diplomas/151837/ site.
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
Built Distribution
Hashes for double_cartpole_custom_gym_env-1.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | b6ce0346cc765a5ddac4fcff21e91dd5bbcc4e88c6ac51456b7201a81bc78c9f |
|
MD5 | b470204230529577427b3f6c847244ed |
|
BLAKE2b-256 | 4fe8e6478c576fbcdda621d2ec88515eb8f346700841730463e484ff3e009187 |
Hashes for double_cartpole_custom_gym_env-1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | eb2a992bce4593997d36adf775ea382a1595f50874adc45e3f6d3d4aeb1ef4d4 |
|
MD5 | f70003ce85cfb299b378f7c40c2a2399 |
|
BLAKE2b-256 | be14bdc05ef914c0d1c80ed6f4e89a6715542f4f049f994dc1daf3e73bbaba58 |