Finding the optimal exploration-exploitation trade-off online through Bayesian risk estimation and minimization.
Stewart JamiesonJonathan P. HowYogesh A. GirdharPublished in: Artif. Intell. (2024)
Keyphrases
- finding optimal
- bayesian estimation
- online learning
- optimal solution
- conditional expectation
- dynamic programming
- real time
- decision making
- bayesian decision
- efficient optimization
- parameter estimation
- bayesian inference
- estimation error
- closed form
- estimation accuracy
- bayesian methods
- risk assessment
- density estimation
- maximum likelihood
- worst case
- least squares
- objective function
- bayesian networks
- data sets