estimate_1_LBI: Likelihood-Based Inference (LBI)

In multiRL: Reinforcement Learning Tools for Multi-Armed Bandit

Likelihood-Based Inference (LBI)

Description

This function provides a unified interface to multiple algorithm packages, allowing different optimization algorithms to be selected for estimating optimal model parameters. The entire optimization framework is based on the log-likelihood returned by the model (or object function), making this function a collection of likelihood-based inference (LBI) methods. By abstracting over algorithm-specific implementations, the function enables flexible and consistent parameter estimation across different optimization backends.

Usage

estimate_1_LBI(env, model, lower, upper, control = list(), ...)

Arguments

env	multiRL.env
model	Reinforcement Learning Model
lower	Lower bound of free parameters
upper	Upper bound of free parameters
control	Settings manage various aspects of the iterative process, see control
...	Additional arguments passed to internal functions.

Value

An S4 object of class multiRL.model generated using the estimated optimal parameters.

multiRL documentation built on March 31, 2026, 5:06 p.m.