-
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.
C++ ★ 8.7k 1mo agoExplain → -
reinforcement_learning
Interaction-side integration library for Reinforcement Learning loops: Predict, Log, [Learn,] Update
C++ ★ 74 3mo agoExplain → -
coba
Contextual bandit benchmarking
Python ★ 53 5mo agoExplain → -
jupyter-notebooks
Vowpal Wabbit examples and tutorials
Jupyter Notebook ★ 21 4y agoExplain → -
estimators
Estimators to perform off-policy evaluation
Python ★ 13 1y agoExplain → -
py-vowpal-wabbit-next
Experimental new Python bindings for the VowpalWabbit library
Python ★ 12 2y agoExplain → -
docker-images
Docker images used for continuous integration
Dockerfile ★ 9 1y agoExplain → -
workshop
No description.
Jupyter Notebook ★ 7 2y agoExplain → -
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.
Jupyter Notebook ★ 5 2y agoExplain → -
neurips2019
No description.
★ 5 6y agoExplain → -
slates-experiments
No description.
Jupyter Notebook ★ 5 6y agoExplain → -
rl_chain
No description.
Python ★ 5 2y agoExplain → -
data-science
No description.
Python ★ 5 5mo agoExplain → -
docs
Genenerated documentation
HTML ★ 4 1mo agoExplain → -
vowpalwabbit.github.io
Official website of Vowpal Wabbit
HTML ★ 4 2y agoExplain → -
icml2019
No description.
★ 4 7y agoExplain → -
slope-experiments
No description.
Python ★ 4 6y agoExplain → -
ccb-experiments
No description.
C++ ★ 3 6y agoExplain → -
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.
★ 2 6y agoExplain → -
autogen ⑂
Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ
Jupyter Notebook ★ 1 2y agoExplain → -
rl_loop_deployment
Deploy RL Loop in Azure
Bicep ★ 1 1y agoExplain → -
rl_loop_image
No description.
★ 1 1y agoExplain → -
agenda
No description.
★ 1 4y agoExplain → -
langchain ⑂
⚡ Building applications with LLMs through composability ⚡
Python ★ 0 2y agoExplain →
No repos match these filters.