Vowpal Wabbit's repositories
vowpal_wabbit
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
reinforcement_learning
Interaction-side integration library for Reinforcement Learning loops: Predict, Log, [Learn,] Update
jupyter-notebooks
Vowpal Wabbit examples and tutorials
estimators
Estimators to perform off-policy evaluation
py-vowpal-wabbit-next
Experimental new Python bindings for the VowpalWabbit library
docker-images
Docker images used for continuous integration
learn_to_pick
A python library for online learning in RL loops, specialized for Contextual Bandit scenarios. Choose actions from multiple options, evaluate decisions, and integrate feedback for improved future outcomes. Features versatile scoring, advanced featurization, and configurable learning policies.
vowpalwabbit.github.io
Official website of Vowpal Wabbit
feature-broker
Mature software applications are highly componentized and have well-defined API boundaries among components. This structure leads to constraints making in-process inference challenging due to the difficulty of access to features. The FeatureBroker library presents a solution to this problem. This helped with adoption of VW in inference. We believe that this is a pervasive problem. The goal of open sourcing this library is to reduce the developer friction in adopting VW in software stacks that are built with these constraints.
rl_loop_deployment
Deploy RL Loop in Azure