gkswamy98/causal_il
Contains implementation of the DoubIL and ResiduIL algorithms from the ICML '22 paper Causal Imitation Learning under Temporally Correlated Noise.
This project helps researchers and practitioners in machine learning and robotics improve how autonomous agents learn from demonstrations, especially when the environment has unpredictable, time-dependent disruptions. It takes recorded actions and observations from an expert and produces a policy that allows an agent to mimic that expert's behavior more robustly, even in noisy or complex settings. This is useful for anyone designing intelligent systems that need to operate reliably in the real world.
No commits in the last 6 months.
Use this if you are training an AI agent to perform tasks by observing an expert, and you suspect that environmental noise or unmeasured factors are making it hard for your agent to learn effectively.
Not ideal if you are looking for a pre-trained agent or a ready-to-deploy solution, as this tool focuses on research and experimentation into imitation learning algorithms.
Stars
11
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Dec 09, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gkswamy98/causal_il"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
py-why/dowhy
DoWhy is a Python library for causal inference that supports explicit modeling and testing of...
py-why/EconML
ALICE (Automated Learning and Intelligence for Causation and Economics) is a Microsoft Research...
uber/causalml
Uplift modeling and causal inference with machine learning algorithms
cdt15/lingam
Python package for causal discovery based on LiNGAM.
andrewtavis/causeinfer
Machine learning based causal inference/uplift in Python