algorithm

The package supports the following eight optimization packages for finding 
 the optimal values of the model's free parameters 
 (default: global = "NLOPT_GN_MLSL", local = "NLOPT_LN_BOBYQA").

A flexible general-purpose toolbox for implementing Rescorla-Wagner models
in multi-armed bandit tasks.
As the successor and functional extension of the 'binaryRL' package,
'multiRL' modularizes the Markov Decision Process (MDP) into six core
components. This framework enables users to construct custom models via
intuitive if-else syntax and define latent learning rules for agents.
For parameter estimation, it provides both likelihood-based
inference (MLE and MAP) and simulation-based inference (ABC and
RNN), with full support for parallel processing across subjects.
The workflow is highly standardized, featuring four main functions
that strictly follow the four-step protocol (and ten rules)
proposed by Wilson & Collins (2019) <doi:10.7554/eLife.49547>.
Beyond the three built-in models (TD, RSTD, and Utility), users
can easily derive new variants by declaring which variables are
treated as free parameters.

YuKi 

multiRL

Reinforcement Learning Tools for Multi-Armed Bandit

Xinyu 

algorithm function

<code>algorithm [Character]</code>

Class

<ol>
<li>L-BFGS-B (from <code><a href="/link/stats%3A%3Aoptim?package=multiRL&version=0.3.7" data-mini-rdoc="multiRL::stats::optim">stats::optim</a></code>)</li>
<li>Simulated Annealing (<code>GenSA::GenSA</code>)</li>
<li>Genetic Algorithm (<code>GA::ga</code>)</li>
<li>Differential Evolution (<code>DEoptim::DEoptim</code>)</li>
<li>Bayesian Optimization (<code>mlrMBO::mbo</code>)</li>
<li>Particle Swarm Optimization (<code>pso::psoptim</code>)</li>
<li>Covariance Matrix Adapting Evolutionary Strategy (<code>cmaes::cma_es</code>)</li>
<li>Nonlinear Optimization (<code><a href="/link/nloptr%3A%3Anloptr?package=multiRL&version=0.3.7" data-mini-rdoc="multiRL::nloptr::nloptr">nloptr::nloptr</a></code>)</li>
</ol>

Packages

<pre><code> # supported algorithms
control = list(
 algorithm = c(
 "L-BFGS-B", "GenSA", "GA", "DEoptim",
 "Bayesian", "PSO", "CMA-ES", "NLOPT_GN_MLSL"
 )
)
</code></pre>

Example

Algorithm Packages (MLE, MAP) — algorithm

<ol>
<li>L-BFGS-B (from <code><a href='https://rdrr.io/r/stats/optim.html'>stats::optim</a></code>)</li>
<li>Simulated Annealing (<code>GenSA::GenSA</code>)</li>
<li>Genetic Algorithm (<code>GA::ga</code>)</li>
<li>Differential Evolution (<code>DEoptim::DEoptim</code>)</li>
<li>Bayesian Optimization (<code>mlrMBO::mbo</code>)</li>
<li>Particle Swarm Optimization (<code>pso::psoptim</code>)</li>
<li>Covariance Matrix Adapting Evolutionary Strategy (<code>cmaes::cma_es</code>)</li>
<li>Nonlinear Optimization (<code><a href='https://rdrr.io/pkg/nloptr/man/nloptr.html'>nloptr::nloptr</a></code>)</li>
</ol>

algorithm: Algorithm Packages (MLE, MAP)

Description

Arguments

Class

Packages

Example