Gym Environments and Implementing Reinforcement Learning Agents with Stable Baselines

Assignment for Introduction to Intelligent Autonomous Systems, 3º Year, 1º Semester, Bachelor in Artificial Intelligence and Data Science.

Summary

The aim of the project is to implement a reinforcement learning agent using the stable baselines library algorithms and test it with the open-source Python library Gymnasium on this gym environment.

Autores:

• Margarida Vila Chã
• Sebastião Santos Lessa

Versões

The versions of the operating systems used to develop and test this application are:

• Fedora 38
• macOS Sonoma 14.0

Python Versions:

• 3.10.0

Requirements

To keep everything organized and simple, we will use MiniConda to manage our environments.

To create an environment with the required packages for this project, run the following commands:

conda create -n GymEnv python=3.10 pytorch::pytorch torchvision torchaudio -c pytorch

Then we need to install the requirements:

pip install -r requirements.txt

Results

The experiments are in this notebook.

TQC in the original environment:	TQC in the wrapped environment

TRPO in the wrapped environment:	PPO in the wrapped environment: