CausalML/doubly-robust-dropel

Off-Policy Evaluation and Learning that is both Doubly Robust and Distributionally Robust.

35
/ 100
Emerging

This project helps researchers and practitioners evaluate and learn new decision-making policies using past observational data, particularly when there's a risk that the future environment might differ from where the data was collected. It takes historical data on past actions, observed outcomes, and the likelihood of taking those actions, and outputs robust estimates of how well a new policy would perform, or even suggests improved policies. This is ideal for data scientists, statisticians, or machine learning engineers working on optimizing policies in fields like healthcare, marketing, or operations research.

No commits in the last 6 months.

Use this if you need to reliably assess or improve a decision-making policy using existing data, and you're concerned about how well your policy will generalize to slightly different future conditions.

Not ideal if you can freely experiment with policies in the real world, or if you're not concerned about potential shifts in the environment where your policy will be deployed.

off-policy-evaluation reinforcement-learning causal-inference decision-making policy-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

10

Forks

3

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 14, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CausalML/doubly-robust-dropel"

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