estimate_1_MAP: Estimation Method: Maximum A Posteriori (MAP)

In multiRL: Reinforcement Learning Tools for Multi-Armed Bandit

Estimation Method: Maximum A Posteriori (MAP)

Description

This function first performs a maximum likelihood estimation (MLE) to obtain the best-fitting parameters for all subjects based on maximum likelihood. It then computes the likelihood-based posterior using user-specified prior distributions. Based on the current group-level data, the prior distributions are subsequently updated. This procedure is iteratively repeated until the likelihood-based posterior converges. The entire process is referred to as Expectation-Maximization with Maximum A Posteriori estimation(EM-MAP).

Usage

estimate_1_MAP(
  data,
  colnames,
  behrule,
  ids = NULL,
  models,
  funcs = NULL,
  priors,
  settings = NULL,
  lowers,
  uppers,
  control,
  ...
)

Arguments

data	A data frame in which each row represents a single trial, see data
colnames	Column names in the data frame, see colnames
behrule	The agent's implicitly formed internal rule, see behrule
ids	The Subject ID of the participant whose data needs to be fitted.
models	Reinforcement Learning Models
funcs	The functions forming the reinforcement learning model, see funcs
priors	Prior probability density function of the free parameters, see priors
settings	Other model settings, see settings
lowers	Lower bound of free parameters in each model.
uppers	Upper bound of free parameters in each model.
control	Settings manage various aspects of the iterative process, see control
...	Additional arguments passed to internal functions.

Value

An S3 object of class DataFrame containing, for each model, the estimated optimal parameters and associated model fit metrics.

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