Multi-armed Bandit with Additional Observations
| Autor: | Alexandre Proutiere, Jinwoo Shin, Donggyu Yun, Yung Yi, Sumyeong Ahn |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Mathematical optimization
Computer Networks and Communications Computer science 020206 networking & telecommunications 02 engineering and technology 010501 environmental sciences 01 natural sciences Multi-armed bandit 010104 statistics & probability Hardware and Architecture 0202 electrical engineering electronic engineering information engineering Reinforcement learning 0101 mathematics Online algorithm Software 0105 earth and related environmental sciences |
| Zdroj: | SIGMETRICS (Abstracts) |
| DOI: | 10.1145/3219617.3219639 |
| Popis: | We study multi-armed bandit (MAB) problems with additional observations, where in each round, the decision maker selects an arm to play and can also observe rewards of additional arms (within a given budget) by paying certain costs. We propose algorithms that are asymptotic-optimal and order-optimal in their regrets under the settings of stochastic and adversarial rewards, respectively. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|