SDP_multiple_uncertainty: SDP under multiple uncertainty
In cboettig/pdg_control: Pretty Darn Good Control

Description Usage Arguments Value

Computes the SDP solution under the case of growth noise, implementation errors in harvesting, and meaurement errors in the stock assessment.

1
2
3

  SDP_multiple_uncertainty(f, p, x_grid, h_grid, Tmax = 25,
    sigmas = c(sigma_g = 0, sigma_m = 0, sigma_i = 0),
    pdfn = pdfn, profit = function(x, h) pmin(x, h))

`f`	the growth function of the escapement population (x-h) should be a function of f(t, y, p), with parameters p
`p`	the parameters of the growth function
`x_grid`	the discrete values allowed for the population size, x
`h_grid`	the discrete values of harvest levels to optimize over
`sigma`	is the shape parameters for noise distribution (sigma_g, sigma_m, sigma_i) (default is no noise)
`pdfn`	is the probability density function (same functional form is used for growth, measure, implement). (Default is uniform)
`profit`	is the profit function (defaults to the realized harvest)

The D matrix giving the optimal harvest for each possible state in each timestep. Hence the optimal policy at time t is given by the policy function D[,t]. Values of D[,t] correspond to the index of h_grid. Indices of of D[,t] correspond to states in y_grid.

cboettig/pdg_control documentation built on May 13, 2019, 2:10 p.m.