Linear Upper Confidence Bound Algorithm for Contextual Bandit Problem with Piled Rewards

Kuan-Hao Huang; Hsuan-Tien Lin

doi:10.1007/978-3-319-31750-2_12

ScienceGate Book Chapters

BOOK-CHAPTER

Linear Upper Confidence Bound Algorithm for Contextual Bandit Problem with Piled Rewards

Kuan-Hao Huang Hsuan-Tien Lin

Year: 2016 Lecture notes in computer science Pages: 143-155 Publisher: Springer Science+Business Media

DOI: 10.1007/978-3-319-31750-2_12

Get Full-Text PDF Get Analytical Report

Keywords:

Regret Upper and lower bounds Computer science Context (archaeology) Action (physics) Function (biology) Stochastic game Mathematical optimization Algorithm Interval (graph theory) Artificial intelligence Mathematics Machine learning Mathematical economics

Metrics

Cited By

1.53

FWCI (Field Weighted Citation Impact)

Refs

0.81

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Advanced Bandit Algorithms Research

Social Sciences → Decision Sciences → Management Science and Operations Research

Reinforcement Learning in Robotics

Physical Sciences → Computer Science → Artificial Intelligence

Machine Learning and Algorithms

Physical Sciences → Computer Science → Artificial Intelligence

Linear Upper Confidence Bound Algorithm for Contextual Bandit Problem with Piled Rewards

Metrics

Citation History

Topics

Related Documents

Pairwise Regression with Upper Confidence Bound for Contextual Bandit with Multiple Actions

Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem

Contextual Bandit Learning with Predictable Rewards

Cascaded Algorithm-Selection and Hyper-Parameter Optimization with Extreme-Region Upper Confidence Bound Bandit

Regret lower bound and optimal algorithm for high-dimensional contextual linear bandit