phlippe/BISCUIT

Official code of the paper "BISCUIT: Causal Representation Learning from Binary Interactions" (UAI 2023)

40
/ 100
Emerging

This project helps researchers and scientists understand the underlying cause-and-effect relationships in complex systems. It takes raw observational data from interactive environments, like robotic simulations or embodied AI platforms, and processes it to reveal distinct causal variables. The primary users are researchers in fields like robotics, AI, and reinforcement learning who need to dissect causal factors from observed binary interactions.

No commits in the last 6 months.

Use this if you are a researcher working with binary interaction data from environments like robotic arms or simulated agents and need to discover causal representations.

Not ideal if your data does not involve binary interactions or if you are not working within research domains that focus on causal representation learning.

Causal Inference Robotics Embodied AI Reinforcement Learning Scientific Research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

39

Forks

9

Language

Python

License

Last pushed

Mar 12, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/phlippe/BISCUIT"

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