For every pair with f_j < f_i, firefly i moves by beta0 exp(-gamma r^2)
(x_j - x_i) + alpha (u - 1/2)(hi - lo), r measured on the unit-scaled box;
alpha decays by delta each iteration.
Usage
FireflyAlgorithm(
f,
bounds,
alpha = 0.5,
beta0 = 1,
gamma = 1,
delta = 0.97,
n_pop = 20,
max_iter = 200,
seed = 0
)
Arguments
- f
Objective to minimise.
- bounds
List of c(low, high) pairs or a two-column matrix.
- alpha
Initial randomisation weight.
- beta0, gamma
Attractiveness parameters.
- delta
Decay of alpha.
- n_pop
Population size.
- max_iter
Iterations.
- seed
Philox seed.
Value
list(x, fun, estimate, history, n_fev, method).
References
Yang, X.-S. (2009). Firefly algorithms for multimodal
optimization. Stochastic Algorithms: Foundations and Applications (SAGA
2009), LNCS 5792, 169-178.
Examples
FireflyAlgorithm(function(x) sum(x^2), list(c(-5, 5), c(-5, 5)), n_pop = 10, max_iter = 20)$fun
#> [1] 0.001409822
