write_momdpx

write_momdpx(P_full, P_par, O, R, gamma, b_full, b_par = rep(1/dim(O)[1],
  dim(O)[1]), file = "input.pomdpx", digits = 4, digits2 = 10,
  format = "f")

Arguments

P_full

transition matrix for fully observable states

P_par

transition matrix for partially observable states

O

observation matrix

R

reward

gamma

discount factor

b_full

initial fully observable state

b_par

initial belief of partially observable states

file

pomdpx file to create

digits

precision to round to before normalizing. Leave at 4 since sarsop seems unable to do more?

digits2

precision to write solution to. Leave at 10, since normalizing requires additional precision

format

floating point format, because sarsop parser doesn't seem to know scientific notation