Results 131 to 140 of about 4,126,170 (169)

The necessity of multimodal feedback for learning effective pedagogical policies with reinforcement learning. [PDF]

Sci Rep
Che L, Guo P, Isleem HF, Wang Z.
europepmc   +1 more source

A review on exploration-exploitation trade-off in psychiatric disorders. [PDF]

BMC Psychiatry
Jami A, Abbaszade S, Vahabie AH.
europepmc   +1 more source

Neural and behavioral signatures of policy compression in cognitive control. [PDF]

Cereb Cortex
Liu S, Kikumoto A, Badre D, Gershman SJ.
europepmc   +1 more source

RETRACTED: Armed violent conflict and healthcare-seeking behavior for maternal and child health in sub-Saharan Africa: A systematic review.

PLoS One
Adeyanju GC, Schrage P, Jalo RI, Abreu L, Schaub M.   +4 more
europepmc   +1 more source

Transfer Learning for Contextual Multi-Armed Bandits [PDF]

Annals of Statistics
Motivated by a range of applications, we study in this paper the problem of transfer learning for nonparametric contextual multi-armed bandits under the covariate shift model, where we have data collected on source bandits before the start of the target bandit learning.
Tony Cai, Hongzhe Li
exaly   +5 more sources

Some of the next articles are maybe not open access.

Related searches:

MABWISER: Parallelizable Contextual Multi-Armed Bandits

International Journal on Artificial Intelligence Tools, 2021
Contextual multi-armed bandit algorithms are an effective approach for online sequential decision-making problems. However, there are limited tools available to support their adoption in the community. To fill this gap, we present an open-source Python library with context-free, parametric and non-parametric contextual multi-armed bandit algorithms ...
Serdar Kadioglu, Emily Strong, Bernard Kleynhans   +2 more
exaly   +2 more sources

Survey on Applications of Multi-Armed and Contextual Bandits

2020 IEEE Congress on Evolutionary Computation (CEC), 2020
In recent years, the multi-armed bandit (MAB) framework has attracted a lot of attention in various applications, from recommender systems and information retrieval to healthcare and finance. This success is due to its stellar performance combined with attractive properties, such as learning from less feedback.
Irina Rish, Djallel Bouneffouf
exaly   +3 more sources

Multi-Objective Contextual Multi-Armed Bandit With a Dominant Objective [PDF]

IEEE Transactions on Signal Processing, 2018
In this paper, we propose a new multi-objective contextual multi-armed bandit (MAB) problem with two objectives, where one of the objectives dominates the other objective. Unlike single-objective MAB problems in which the learner obtains a random scalar reward for each arm it selects, in the proposed problem, the learner obtains a random reward vector,
Eralp Turgay, Cem Tekin
exaly   +6 more sources