Python-Based Reinforcement Learning on Simulink Models

TL;DR

This paper introduces a Python-based framework for training reinforcement learning agents on Simulink models, enabling seamless transfer to real systems and leveraging Python's flexibility for control tasks.

Contribution

It presents a novel integration method combining Simulink and Python for reinforcement learning, including C-code generation and Python interface development.

Findings

Policies trained in Simulink transfer effectively to real systems.

The framework outperforms previous methods in training efficiency.

Demonstrates successful control of Quanser Aero 2 helicopter.

Abstract

This paper proposes a framework for training Reinforcement Learning agents using Python in conjunction with Simulink models. Leveraging Python's superior customization options and popular libraries like Stable Baselines3, we aim to bridge the gap between the established Simulink environment and the flexibility of Python for training bleeding edge agents. Our approach is demonstrated on the Quanser Aero 2, a versatile dual-rotor helicopter. We show that policies trained on Simulink models can be seamlessly transferred to the real system, enabling efficient development and deployment of Reinforcement Learning agents for control tasks. Through systematic integration steps, including C-code generation from Simulink, DLL compilation, and Python interface development, we establish a robust framework for training agents on Simulink models. Experimental results demonstrate the effectiveness of our approach, surpassing previous efforts and highlighting the potential of combining Simulink with Python for Reinforcement Learning research and applications.