Documentdetail
ID kaart
oai:arXiv.org:2408.15535
Onderwerp
Computer Science - Machine Learnin... Computer Science - Artificial Inte...Auteur
Jeong, Woojin Min, SeungkiCategorie
Computer Science
Jaar
2024
vermelding datum
04-09-2024
Trefwoorden
budgeted budget algorithms sampling thompsonBeschrijving
We consider a Bayesian budgeted multi-armed bandit problem, in which each arm consumes a different amount of resources when selected and there is a budget constraint on the total amount of resources that can be used.
Budgeted Thompson Sampling (BTS) offers a very effective heuristic to this problem, but its arm-selection rule does not take into account the remaining budget information.
We adopt \textit{Information Relaxation Sampling} framework that generalizes Thompson Sampling for classical $K$-armed bandit problems, and propose a series of algorithms that are randomized like BTS but more carefully optimize their decisions with respect to the budget constraint.
In a one-to-one correspondence with these algorithms, a series of performance benchmarks that improve the conventional benchmark are also suggested.
Our theoretical analysis and simulation results show that our algorithms (and our benchmarks) make incremental improvements over BTS (respectively, the conventional benchmark) across various settings including a real-world example.
;Comment: accepted
Jeong, Woojin,Min, Seungki, 2024, Improving Thompson Sampling via Information Relaxation for Budgeted Multi-armed Bandits
VertiSelector: Automatic Curriculum Learning for Wheeled Mobility on Vertically Challenging Terrain
sampling training learning vs
Comparison between Dual-Energy CT and Quantitative Susceptibility Mapping in Assessing Brain Iron Deposition in Parkinson Disease
nigra substantia healthy depositions p < 05 nucleus brain susceptibility ct bilateral dual-energy iron quantitative mapping values magnetic globus pallidus
