Introduction

CartER [Cartpole Environment for Reinforcement learning] is an open-source learning platform that enables the user to quickly start experimenting with simulated and physical multi-agent reinforcement learning projects.

CartER is still being actively developed and uses different strategies for balancing a cartpole ranging from state-of-the-art reinforcement-learning libraries to control theory for greater reproducibility.

This documentation describes the additional component developed to achieve a fully automated setup and enable data analysis across different PID parameter sets. My 2025 summer internhip work is based on the project accomplished by Zhen and Owen during 2023 summer

Author

This is the continuation of the CartER projects undertaken by Jeppe and Will.

The CartER project is an undergraduate research project at the Biological and Soft Systems group at Cavendish Laboratory, University of Cambridge under supervision of Professor Pietro Cicuta.

Queries for this section can be made to ananyapriyaroop@iitb.ac.in or through the GitHub repository located at ANOsapien/CartER

Documentation overview

It is divided into a number of categories:

• Development: Documentation surrounding the development of the project.
  Useful for advanced use or further development of the platform.
• Assembly: Documentation on acquiring hardware, 3D-printing parts, and assemblying the project.
• Articles: A collection of articles related to the project.
• Videos: A collection of videos of the project in action.