This presentation contains very precise yet detailed explanation of concepts of a very interesting topic -- Reinforcement Learning.

Adversarial multi-armed bandit algorithms

A/B testing metrics collection with golang

Online learning approaches to optimize database join operations in PostgreSQL.

Research project on automated A/B testing of software by evolutionary bandits.

Solutions to the Stanford CS:234 Reinforcement Learning 2022 course assignments.

Network-Oriented Repurposing of Drugs Python Package

A small collection of Bandit Algorithms (ETC, E-Greedy, Elimination, UCB, Exp3, LinearUCB, and Thompson Sampling)

Reinforcement learning

Movie Recommendation using Cascading Bandits namely CascadeLinTS and CascadeLinUCB

Client that handles the administration of StreamingBandit online, or straight from your desktop. Setup and run streaming (contextual) bandit experiments in your browser.

Solutions and figures for problems from Reinforcement Learning: An Introduction Sutton&Barto

Privacy-Preserving Bandits (MLSys'20)

Another A/B test library

Contextual bandit algorithm called LinUCB / Linear Upper Confidence Bounds as proposed by Li, Langford and Schapire

Thompson Sampling Tutorial