conftrace_

2011 NeurIPS NeurIPS 2011

An Empirical Evaluation of Thompson Sampling

Abstract

Thompson sampling is one of oldest heuristic to address the exploration / exploitation trade-off, but it is surprisingly not very popular in the literature. We present here some empirical results using Thompson sampling on simulated and real data, and show that it is highly competitive. And since this heuristic is very easy to implement, we argue that it should be part of the standard baselines to compare against.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

🧭 Keyword Pioneer - thompson sampling

🐣 Hot Topic Early Bird - thompson sampling

Authors

Olivier Chapelle, Lihong Li

Topics

Artificial Intelligence > Core AI > Multi-Agent Systems Artificial Intelligence > Bayesian & Probabilistic > Bayesian Learning Machine Learning > Optimization & Theory > Bayesian Inference Mathematics & Optimization > Optimization > Stochastic Methods Machine Learning > Optimization & Theory > Stochastic Methods Artificial Intelligence > Bayesian & Probabilistic > Bayesian Inference Machine Learning > Learning Types > Multi-Armed Bandits Artificial Intelligence > Core AI > Reinforcement Learning

Keywords

online learning bayesian inference sequential decision making exploration-exploitation tradeoff exploration exploitation thompson sampling empirical evaluation multi-armed bandit bayesian method

More from NeurIPS 2011

All NeurIPS 2011 papers →

Improved Algorithms for Linear Stochastic Bandits

From Bandits to Experts: On the Value of Side-Observations

Optimal Reinforcement Learning for Gaussian Systems

Efficient Offline Communication Policies for Factored Multiagent POMDPs

Maximal Cliques that Satisfy Hard Constraints with Application to Deformable Object Model Learning

Quasi-Newton Methods for Markov Chain Monte Carlo