MLPro - Machine Learning Professional
Welcome to MLPro - the synoptic framework for standardized machine learning tasks in Python!
MLPro provides complete, standardized and reusable functionalities to support your scientific research, industrial projects or educational tasks in machine learning.
The documentation is currently under construction, but we are working flat out to complete it. The framework itself is ready for use and we are proud to offer you extensive functionalities, especially in the area of reinforcement learning and game theory. A number of self-study examples are available in Appendix 1 and the API documentation in Appendix 2 is pretty complete. Try it out and get in touch with any questions or problems. Have fun!
Table of Content
1 Introduction
2 MLPro-BF – Basic Functions
3 MLPro-SL - Supervised Learning
4 MLPro-RL – Reinforcement Learning
5 MLPro-GT – Game Theory
6 MLPro-UI – Interactive ML
Appendix 1: Examples
- Basic Functions
- Reinforcement Learning
- Howto 01 - (RL) Types of reward
- Howto 02 - (RL) Run agent with own policy with gym environment
- Howto 03 - (RL) Train agent with own policy on gym environment
- Howto 04 - (RL) Run multi-agent with own policy in multicartpole environment
- Howto 05 - (RL) Train multi-agent with own policy on multicartpole environment
- Howto 10 - (RL) Train using SB3 Wrapper
- Howto 11 - (RL) Wrap mlpro Environment class to gym environment
- Howto 12 - (RL) Wrap mlpro Environment class to petting zoo environment
- Howto 13 - (RL) Comparison Native and Wrapper SB3 Policy
- Howto 14 - (RL) Train UR5 with SB3 wrapper
- Howto 15 - (RL) Train Robothtm with SB3 Wrapper
- Game Theory
- User Interface
Appendix 2: API Reference
Appendix 3: Project MLPro
Citing MLPro
To cite this project in publications:
@misc{...
}
Contact Data
Mail: mlpro@listen.fh-swf.de