TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
-
Updated
Jul 8, 2024 - Python
TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
Open Bandit Pipeline: a python library for bandit algorithms and off-policy evaluation
[IJAIT 2021] MABWiser: Contextual Multi-Armed Bandits Library
An easy-to-use reinforcement learning library for research and education.
A Pythonic microframework for multi-armed bandit problems
Python implementation of UCB, EXP3 and Epsilon greedy algorithms
This project is created for the simulations of the paper: [Wang2021] Wenbo Wang, Amir Leshem, Dusit Niyato and Zhu Han, "Decentralized Learning for Channel Allocation inIoT Networks over Unlicensed Bandwidth as aContextual Multi-player Multi-armed Bandit Game", to appear in IEEE Transactions on Wireless Communications, 2021.
Learning Multi-Armed Bandits by Examples. Currently covering MAB, UCB, Boltzmann Exploration, Thompson Sampling, Contextual MAB, Deep MAB.
Bayesian Optimization for Categorical and Continuous Inputs
Online Ranking with Multi-Armed-Bandits
Implementations of basic concepts dealt under the Reinforcement Learning umbrella. This project is collection of assignments in CS747: Foundations of Intelligent and Learning Agents (Autumn 2017) at IIT Bombay
Decentralized Intelligent Resource Allocation for LoRaWAN Networks
A beer recommendation system using multi-armed bandit approach to solve cold start problems
[NeurIPS 2022] Supervising the Multi-Fidelity Race of Hyperparameter Configurations
Implementation of the X-armed Bandits algorithm, as detailed in the paper, "X-armed Bandits", Bubeck et al., 2011.
A multi-armed bandit (MAB) simulation library in Python
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.
An improved version of Turbo algorithm for the Black-box optimization competition organized by NeurIPS 2020
Multi-Armed Bandit method of accurately estimating the largest parameter out of a set of candidates.
Add a description, image, and links to the multi-armed-bandits topic page so that developers can more easily learn about it.
To associate your repository with the multi-armed-bandits topic, visit your repo's landing page and select "manage topics."