/* 

  Sally and the vending machine (1) in Picat.

  From https://probmods.org/chapters/social-cognition (WebPPL model)
  """
  For instance, imagine that Sally walks up to a vending machine wishing to have a cookie. 
  Imagine also that we know the mapping between buttons (potential actions) and foods 
  (outcomes). We can then predict Sally’s action: 
    <the WebPPL model>
  We see, unsurprisingly, that if Sally wants a cookie, she will always press button b.
  """

  Cf my Gamble model gamble_vending_machine1.rkt

  This program was created by Hakan Kjellerstrand, hakank@gmail.com
  See also my Picat page: http://www.hakank.org/picat/

*/

import ppl_distributions, ppl_utils.
import util.

main => go.

/*

  var : v
  Probabilities:
  b: 1.0000000000000000
  mean = [b = 1.0]

*/
go ?=>
  reset_store,
  run_model(10_000,$model,[show_probs_trunc,mean]),
  nl,
  % show_store_lengths,nl,
  % fail,
  nl.
go => true.
  

vending_machine(State,Action) = Res =>
  Res = case(Action,
             [[a,bagel],
              [b,cookie],
              [true,nothing]]).

choose_action(GoalState,Transition,ActionPrior) = choose_action(GoalState, Transition, ActionPrior, undefined).
choose_action(GoalState, Transition, ActionPrior, State1) = Res =>
  State = cond(State1 == undefined,start,state1),
  Action = ActionPrior,
  observe(GoalState == apply(Transition,State,Action)),
  Res = Action.

model() =>
  ActionPrior = categorical([0.5,0.5],[a,b]),

  V = choose_action(cookie,vending_machine,ActionPrior),
    
  if observed_ok then
    add("v",V),
  end.