Skip to content
@VowpalWabbit

Vowpal Wabbit

Pinned Loading

  1. vowpal_wabbit Public

    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 lea…

    C++ 8.5k 1.9k

  2. reinforcement_learning Public

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

    C++ 75 40

Repositories

Showing 10 of 24 repositories
  • docker-images Public

    Docker images used for continuous integration

    Dockerfile 9 MIT 13 2 1 Updated Nov 5, 2024
  • reinforcement_learning Public

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

    C++ 75 MIT 40 51 (6 issues need help) 17 Updated Nov 4, 2024
  • vowpal_wabbit Public

    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++ 8,541 1,929 132 (5 issues need help) 4 Updated Oct 17, 2024
  • coba Public

    Contextual bandit benchmarking

    Python 49 BSD-3-Clause 19 1 1 Updated Sep 3, 2024
  • estimators Public

    Estimators to perform off-policy evaluation

    Python 13 BSD-3-Clause 17 16 3 Updated Sep 3, 2024
  • docs Public

    Genenerated documentation

    HTML 4 3 1 0 Updated Aug 22, 2024
  • rl_loop_deployment Public

    Deploy RL Loop in Azure

    Bicep 1 MIT 0 0 0 Updated Aug 5, 2024
  • rl_loop_image Public
    1 0 0 0 Updated Aug 5, 2024
  • autogen Public Forked from microsoft/autogen

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

    Jupyter Notebook 0 CC-BY-4.0 6,381 0 3 Updated Jan 18, 2024
  • learn_to_pick Public

    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 MIT 4 7 0 Updated Nov 28, 2023
View all repositories

Top languages

Loading…

Most used topics

Loading…