MLPro-Int-SB3 - Integration of Stable-Baselines3 into MLPro

Welcome to MLPro-Int-SB3, an extension to MLPro to integrate the Stable-Baselines3 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. Stable-Baselines3, in turn, provides a diverse suite of reliable implementations of reinforcement learning algorithms in PyTorch.

MLPro-Int-SB3 offers wrapper classes that allow the reuse of environments from Stable-Baselines3 in MLPro, or the other way around.

Preparation

Before running the examples, please install the latest versions of MLPro, Stable-Baselines3, and MLPro-Int-SB3 as follows:

pip install mlpro-int-sb3[full] --upgrade

See also

• MLPro - Machine Learning Professional

• MLPro-RL - Sub-framework for reinforcement learning

• Stable-Baselines3 - Reliable Reinforcement Learning Implementations

• Further MLPro extensions

• MLPro-Int-SB3 on GitHub

Example Pool

• Basic Wrapper Functionalities
  • Howto RL-WP-001: Train an Agent with SB3
  • Howto RL-WP-002: Validation SB3 Wrapper (On-Policy)
  • Howto RL-WP-003: Validation SB3 Wrapper (Off-Policy)
• Agent
  • Howto RL-AGENT-001: Train and Reload Single Agent (Gymnasium)
• Environment
  • Howto RL-ENV-001: SB3 Policy on RobotHTM Environment
• Advanced Training Techniques
  • Howto RL-ATT-001: Train and Reload Single Agent using Stagnation Detection (Gymnasium)
• Model-based RL
  • Howto RL-MB-001: Train and Reload Model Based Agent (Gym)
  • Howto RL-MB-002: MBRL on RobotHTM Environment

API Reference

• Wrapper Root Class
  • DummyEnv
  • VecExtractDictObs
  • WrPolicySB32MLPro

About

• Release Notes
• Disclaimer
  • Disclaimers for MLPro Usage
  • Consent