MLPro-Int-Gymnasium - Integration between Gymnasium and MLPro
Welcome to MLPro-Int-Gymnasium, an extension to MLPro to integrate the Gymnasium package. MLPro is a middleware framework for standardized machine learning in Python. It is developed by the South Westphalia University of Applied Sciences, Germany, and provides standards, templates, and processes for hybrid machine learning applications. Gymnasium, in turn, provides a diverse suite of reinforcement learning environments.
MLPro-Int-Gymnasium offers wrapper classes that allow the reuse of environments from Gymnasium in MLPro, or the other way around.
Preparation
Before running the examples, please install the latest versions of MLPro, Gymnasium, and MLPro-Int-Gymnasium as follows:
pip install mlpro-int-gymnasium[full] --upgrade
Environments and Boards
Example pool
- Reinforcement Learning
- Howto RL-AGENT-001: Run an Agent with Own Policy on Gym Environment
- Howto RL-AGENT-002: Train an Agent with Own Policy on Gym Environment
- Howto RL-AGENT-003: Run Multi-Agent with Own Policy on Gym Environment
- Howto RL-AGENT-004: Train Multi-Agent with Own Policy on Gym Environment
- Howto RL-AGENT-010: Train a SB3 PPO Agent on the Rubik’s Cube 2x2x2 Environment
- Howto RL-WP-001: MLPro Environment to Gymnasium Environment
- Howto RL-WP-002: Gymnasium Environment to MLPro Environment
- Dynamic Games in Game Theory
API reference