A Neural Networks Committee for the Contextual Bandit Problem
By Robin Allesiardo, Raphaël Féraud, Djallel Bouneffouf. 2014
93 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Management Science and Operations Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- George Tucker
- Quanquan Gu
- Sergey Levine
- Lihong Li
- Dongruo Zhou
- Jasper Snoek
- Ofir Nachum
- Carlos Riquelme
In Management Science and Operations Research
- George Tucker
- Quanquan Gu
- Dongruo Zhou
- Lihong Li
- Jasper Snoek
- Carlos Riquelme
- Sergey Levine
- Ofir Nachum
Citations in the corpus
- Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling (2018, methodology): “We evaluated the algorithms (see Appendix A) on several bandit problems constructed from real-world datasets ([26, 27, 28] and Appendix B for details).”
- Neural Contextual Bandits with UCB-based Exploration (2019, methodology): “Allesiardo et al. (2014) proposed NeuralBandit which consists of K neural networks.”