Etat de l'art sur l'application des bandits multi-bras

Abstract

The Multi-armed bandit offer the advantage to learn and exploit the already learnt knowledge at the same time. This capability allows this approach to be applied in different domains, going from clinical trials where the goal is investigating the effects of different experimental treatments while minimizing patient losses, to adaptive routing where the goal is to minimize the delays in a network. This article provides a review of the recent results on applying bandit to real-life scenario and summarize the state of the art for each of these fields. Different techniques has been proposed to solve this problem setting, like epsilon-greedy, Upper confident bound (UCB) and Thompson Sampling (TS). We are showing here how this algorithms were adapted to solve the different problems of exploration exploitation.

in French

References in corpus (34)

• Analysis of Thompson Sampling for the multi-armed bandit problem
• Thompson Sampling for Contextual Bandits with Linear Payoffs
• A Survey on Practical Applications of Multi-Armed and Contextual Bandits
• Algorithm Selection as a Bandit Problem with Unbounded Losses
• Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
• Interpretable Multi-Objective Reinforcement Learning through Policy Orchestration
• Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
• Model-Independent Online Learning for Influence Maximization
• Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models
• A Bandit Approach to Posterior Dialog Orchestration Under a Budget
• Online learning with Corrupted context: Corrupted Contextual Bandits
• Towards User Profile Modelling in Recommender System
• Online Semi-Supervised Learning with Bandit Feedback
• Situation-Aware Approach to Improve Context-based Recommender System
• Contextual Bandit with Missing Rewards
• How can AI Automate End-to-End Data Science?
• Hyper-parameter Tuning for the Contextual Bandit
• Mobile Recommender Systems Methods: An Overview
• Context-Based Information Retrieval in Risky Environment
• Optimizing an Utility Function for Exploration / Exploitation Trade-off in Context-Aware Recommender System
• Role of temporal inference in the recognition of textual inference
• Recommandation mobile, sensible au contexte de contenus évolutifs: Contextuel-E-Greedy
• Solving Constrained CASH Problems with ADMM
• Étude des dimensions spécifiques du contexte dans un système de filtrage d'informations
• Improving adaptation of ubiquitous recommander systems by using reinforcement learning and collaborative filtering
• Applying machine learning techniques to improve user acceptance on ubiquitous environement
• R-UCB: a Contextual Bandit Algorithm for Risk-Aware Recommender Systems
• Exponentiated Gradient LINUCB for Contextual Multi-Armed Bandits
• Computing the Dirichlet-Multinomial Log-Likelihood Function
• The Impact of Situation Clustering in Contextual-Bandit Algorithm for Context-Aware Recommender Systems
• Proposition d'une technique de gestion de projet dans les startups
• Evolution of the user's content: An Overview of the state of the art
• Spectral Clustering using Eigenspectrum Shape Based Nystrom Sampling
• Hybrid Q-Learning Applied to Ubiquitous recommender system