ShengranHu/Thought-Cloning

[NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

40
/ 100
Emerging

This project helps AI researchers and developers train artificial agents to perform tasks more safely and interpretably in simulated environments. It takes a dataset of human actions and corresponding 'thoughts' (internal reasoning) and produces an AI model that not only performs the task but also simulates human-like decision-making processes. This is useful for researchers developing and testing intelligent agents in controlled settings.

268 stars. No commits in the last 6 months.

Use this if you are an AI researcher or developer working with simulated environments and need to train agents that mimic human thinking for enhanced safety and interpretability.

Not ideal if you are looking to deploy AI agents in real-world scenarios or do not have access to human thought datasets for your specific tasks.

AI-safety Reinforcement-Learning Simulated-Environments Agent-Training Interpretability
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

268

Forks

24

Language

Python

License

MIT

Last pushed

Jun 28, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ShengranHu/Thought-Cloning"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.