multi-armed-bandit problem

Demo for NAIST Spring Seminar 2017

R package for Multi-Armed Bandit Simulation Study

A simple implementation of the multi_arm_bandit problem which can be used in Open AI gym as well.

Reinforcement Learning

Implementations of the bandit algorithms with unordered and ordered slates that are described in the paper "Non-Stochastic Bandit Slate Problems", by Kale et al. 2010.

In probability theory, the multi-armed bandit problem is a problem in which a fixed limited set of resources must be allocated between competing (alternative) choices in a way that maximizes their expected gain, when each choice's properties are only partially known at the time of allocation, and may become better understood as time passes or by…

A bandit server that implements the multi-armed bandit for running a single experiment

Reinforcement Learning in Scala

Implementation of the X-armed Bandits algorithm, as detailed in the paper, "X-armed Bandits", Bubeck et al., 2011.

Python implementation of multi-armed bandit using epsilon-greedy exploration and reward-average sampling estimation

Il bandito bracciuto: Introduzione leggera ma non troppo all'apprendimento con rinforzo.

A golang library for solving multi armed bandit problem which can optimize your business choice on the fly without A/B testing

An implementation of solvers for the multi-armed-bandit-problem in JavaScript.

More about the exploration-exploitation tradeoff with harder bandits

Software for the experiments reported in the RecSys 2019 paper "Multi-Armed Recommender System Bandit Ensembles"

A/B Testing Framework for Python (with optional Multi-armed bandit implementation)

Using the Airspeed Velocity tool (https://asv.readthedocs.io/) to benchmark SMPyBandits (https://github.com/SMPyBandits/SMPyBandits/)