LLM-Robotics Article Supplementary Data

This repository contains supplementary material for the article LLMs for sensory-motor control: Combining in-context and iterative learning by Jônata Tyska Carvalho and Stefano Nolfi. It includes:

• 📹 Videos demonstrating the behaviors produced by LLM-driven policies
• 📄 Logs of LLM interactions and system responses
• 🧠 LLM-generated policies (IF-THEN rules and python code) generated by the LLMs
• 🧪 Code for replicating and extending the experiments (located in the code/ directory)

For easy visualization of the supplementary material, use the website: https://jtyska.github.io/llm-robotics-article/

Code Usage

To replicate the experiments:

1. Navigate to the code/ directory.
2. Install the dependencies with setup_requirements.py and run the experiments with run_experiment.py
3. Ensure any required LLM_SERVER_ADDRESS, API keys or model credentials (e.g., Hugging Face) are filled in the proper files.

License

🧑‍💻 Code

The code in this repository is licensed under the MIT License, with the additional restriction that commercial use is not permitted without prior written permission from the authors.

This means you are free to:

• Use, modify, and distribute the code
• As long as you:
  • Provide attribution
  • Do not use it for commercial purposes

📄 Supplementary Materials (Videos, Logs, Policies)

All other non-code content is licensed under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license.

• Learn more: CC BY-NC 4.0

Citation

If you use this data or code in your research, please cite the associated article.