Vowpal Wabbit (VowpalWabbit)

Vowpal Wabbit

VowpalWabbit

Geek Repo

Home Page:https://vowpalwabbit.org

Github PK Tool:Github PK Tool

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.

Language:C++License:NOASSERTIONStargazers:8400Issues:349Issues:1264

reinforcement_learning

Interaction-side integration library for Reinforcement Learning loops: Predict, Log, [Learn,] Update

Language:C++License:MITStargazers:72Issues:14Issues:75

coba

Contextual bandit benchmarking

Language:PythonLicense:BSD-3-ClauseStargazers:41Issues:5Issues:8

jupyter-notebooks

Vowpal Wabbit examples and tutorials

Language:Jupyter NotebookStargazers:19Issues:7Issues:1

estimators

Estimators to perform off-policy evaluation

Language:PythonLicense:BSD-3-ClauseStargazers:12Issues:9Issues:19

py-vowpal-wabbit-next

Experimental new Python bindings for the VowpalWabbit library

Language:PythonLicense:BSD-3-ClauseStargazers:10Issues:2Issues:8

docker-images

Docker images used for continuous integration

Language:DockerfileLicense:MITStargazers:8Issues:6Issues:4
Language:Jupyter NotebookStargazers:6Issues:5Issues:0
Language:PythonLicense:BSD-3-ClauseStargazers:4Issues:6Issues:7
Language:Jupyter NotebookStargazers:4Issues:5Issues:0

docs

Genenerated documentation

Language:PythonLicense:MITStargazers:3Issues:0Issues:0

vowpalwabbit.github.io

Official website of Vowpal Wabbit

Language:HTMLLicense:MITStargazers:3Issues:8Issues:60

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.

Language:Jupyter NotebookLicense:MITStargazers:2Issues:0Issues:0

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.

autogen

Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

Language:Jupyter NotebookLicense:CC-BY-4.0Stargazers:0Issues:0Issues:0

langchain

⚡ Building applications with LLMs through composability ⚡

Language:PythonLicense:MITStargazers:0Issues:0Issues:0