instadeepai/catx
🐈⬛ Contextual bandits library for continuous action trees with smoothing in JAX
This helps data scientists and machine learning engineers who need to make a sequence of continuous decisions in real-time to maximize a desired outcome. You provide the context for a decision and potential actions, and it recommends the best continuous action. This is ideal for optimizing dynamic systems where the best choice isn't always obvious and needs to adapt based on live information.
No commits in the last 6 months. Available on PyPI.
Use this if you need to build a system that learns to make optimal, continuous decisions in an environment where past outcomes inform future choices and exploration of options is important.
Not ideal if your decisions are discrete (e.g., choosing from a fixed list of options) or if you don't require the system to adapt and learn over time.
Stars
71
Forks
3
Language
Python
License
MIT
Category
Last pushed
Oct 07, 2022
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/instadeepai/catx"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/