A Neural Networks Committee for the Contextual Bandit Problem

2014/09/29 by Robin Allesiardo, Allesiardo, Robin, Raphaël Féraud +3 · 1 citation
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Data Stream Mining Techniques #FOS: Computer and information sciences #I.2 #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1409.8191

openalex publication_date 2014/09/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper presents a new contextual bandit algorithm, NeuralBandit, which does not need hypothesis on stationarity of contexts and rewards. Several neural networks are trained to modelize the value of rewards knowing the context. Two variants, based on multi-experts approach, are proposed to choose online the parameters of multi-layer perceptrons. The proposed algorithms are successfully tested on a large dataset with and without stationarity of rewards.

Citations

• Playing Atari with Deep Reinforcement Learning
• The Nonstochastic Multiarmed Bandit Problem
• Thompson Sampling for Contextual Bandits with Linear Payoffs

Cited by

• BanditMF: Multi-Armed Bandit Based Matrix Factorization Recommender System

Related

• Neural Contextual Bandits with UCB-based Exploration
• Neural Contextual Bandits without Regret
• Neural Exploitation and Exploration of Contextual Bandits
• An Efficient Algorithm for Deep Stochastic Contextual Bandits
• Contextual Bandit with Adaptive Feature Extraction