// handwashing pomdp spec
// planstep is as usual  (see http://www.cs.toronto.edu/~jhoey/papers/zmj.pdf)
// behavior describes what the user has just done
// responsive describes if the user will respond to a prompt if given
// aware describes how aware the user is of their current situation
// responsive-aware pairs describe the following (Extreme) user types
// responsive,aware  : user will do the right thing if left alone, but will also respond to prompts
// responsive,!aware : user will not do anything if left alone, but will respond to prompts
// !responsive, aware :   user will do the right thing if left alone, and will ignore prompts
// !responsive,!aware : user will not do anything if left alone, and ignores prompts (e.g. the user is asleep)
(variables 
	(planstep a b c d e g j h k)
	(behavior nothing wet taps soap dry)
	(responsive no yes)
	(aware	    no yes)
)
(observations	(handpos away sink water tap soap towel))
//belief
//	planstep	(1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0)
//	responsive	(0.5 0.5)
//	aware		(0.5 0.5)
//	behavior	(1.0 0.0 0.0 0.0 0.0)
//endbelief
init [* (planstep (a (1.0)) (b (0.0)) (c (0.0)) (d (0.0)) (e (0.0)) (g (0.0)) (h (0.0)) (j (0.0)) (k (0.0)))
        (responsive (no (0.5)) (yes (0.5)))
        (aware (no (0.5)) (yes (0.5)))
        (behavior (nothing (1.0)) (wet (0.0)) (taps (0.0)) (soap (0.0)) (dry (0.0)))]
unnormalised
dd handPosCPT
    (behavior' (nothing   (handpos' (away (0.5))  (sink (0.5))  (water (0.01)) (tap (0.01)) (soap (0.01)) (towel (0.01))))
			  (wet	     (handpos' (away (0.01)) (sink (0.2))  (water (0.5))  (tap (0.01)) (soap (0.01)) (towel (0.01))))
			  (taps	     (handpos' (away (0.01)) (sink (0.1))  (water (0.2))  (tap (0.5))  (soap (0.01)) (towel (0.01))))
			  (soap	     (handpos' (away (0.01)) (sink (0.2))  (water (0.01)) (tap (0.01)) (soap (0.5))  (towel (0.01))))
			  (dry	     (handpos' (away (0.01)) (sink (0.2))  (water (0.1))  (tap (0.01)) (soap (0.01)) (towel (0.5)))))
enddd
dd planstepdd
       (planstep	(a	(behavior'	(nothing	(planstepa))
							(wet		(planstepa))
							(taps		(planstepb))
							(soap		(planstepe))
							(dry		(planstepa))))
				(b	(behavior'	(nothing	(planstepb))
							(wet		(planstepc))
							(taps		(planstepb))
							(soap		(planstepd))
							(dry		(planstepb))))
				(c	(behavior'	(nothing	(planstepc))
							(wet		(planstepc))
							(taps		(planstepc))
							(soap		(planstepd))
							(dry		(planstepb))))
				(d	(behavior'	(nothing	(planstepd))
							(wet		(planstepg))
							(taps		(planstepd))
							(soap		(planstepd))
							(dry		(planstepb))))
				(e	(behavior'	(nothing	(planstepe))
							(wet		(planstepe))
							(taps		(planstepd))
							(soap		(planstepe))
							(dry		(planstepb))))
				(g	(behavior'	(nothing	(planstepg))
							(wet		(planstepg))
							(taps		(plansteph))
							(soap		(planstepd))
							(dry		(planstepj))))
				(h	(behavior'	(nothing	(plansteph))
							(wet		(plansteph))
							(taps		(planstepg))
							(soap		(planstepe))
							(dry		(planstepk))))
				(j	(behavior'	(nothing	(planstepj))
							(wet		(planstepg))
							(taps		(planstepk))
							(soap		(planstepd))
							(dry		(planstepj))))
				(k	(behavior'	(nothing	(planstepk))
							(wet		(planstepk))
							(taps		(planstepj))
							(soap		(planstepe))
							(dry		(planstepk)))))
enddd
dd correctBehavior
      (planstep	(a	[+	(behaviortaps)	(behaviorsoap)])
		(b	[+	(behaviorwet)		(behaviorsoap)])
		(c	(behaviorsoap))
		(d	(behaviorwet))
		(e	(behaviortaps))
		(g	[+	(behaviortaps)	(behaviordry)])
		(h	(behaviordry))
		(j	(behaviortaps))
		(k	(behaviornothing)))
enddd
dd nullBehavior
   (behavior'	(nothing	(0.5))
		(wet		(0.1))
		(taps		(0.1))
		(soap		(0.1))
		(dry		(0.1)))
enddd
dd behDynAware
   (aware'	(yes	[+ (2.0) (correctBehavior)])
		(no	(nullBehavior)))
enddd
dd responseFactor
   (2.0)
enddd
action nothing
       planstep	(planstepdd)
       aware	(SAMEaware)
       responsive	(SAMEresponsive)
       behavior	(behDynAware)
       observe  
            handpos	(handPosCPT)
       endobserve 
endaction
action wet_hands
       planstep	(planstepdd)
       aware	(SAMEaware)
       responsive	(SAMEresponsive)
       behavior	(responsive'	(no	(behDynAware))
				(yes	[+	(behDynAware)	[* (responseFactor) (behaviorwet)]]))
       observe
            handpos	(handPosCPT)
       endobserve
       cost (aware		(no	(0.2))
				(yes	(0.8)))
endaction
action turnon_water
       planstep	(planstepdd)
       aware	(SAMEaware)
       responsive	(SAMEresponsive)
       behavior	(responsive'	(no	(behDynAware))
				(yes	[+	(behDynAware)	[* (responseFactor) (behaviortaps)]]))
       observe
            handpos	(handPosCPT)
       endobserve
       cost (aware		(no	(0.2))
				(yes	(0.8)))
endaction
action turnoff_water
       planstep	(planstepdd)
       aware	(SAMEaware)
       responsive	(SAMEresponsive)
       behavior	(responsive'	(no	(behDynAware))
				(yes	[+	(behDynAware)	[* (responseFactor) (behaviortaps)]]))
       observe
            handpos	(handPosCPT)
       endobserve
       cost (aware		(no	(0.2))
				(yes	(0.8)))
endaction
action use_soap
       planstep	(planstepdd)
       aware	(SAMEaware)
       responsive	(SAMEresponsive)
       behavior	(responsive'	(no	(behDynAware))
				(yes	[+	(behDynAware)	[* (responseFactor) (behaviorsoap)]]))
       observe
            handpos	(handPosCPT)
       endobserve
       cost (aware		(no	(0.2))
				(yes	(0.8)))
endaction
action dry_hands
       planstep	(planstepdd)
       aware	(SAMEaware)
       responsive	(SAMEresponsive)
       behavior	(responsive'	(no	(behDynAware))
				(yes	[+	(behDynAware)	[* (responseFactor) (behaviordry)]]))
       observe
            handpos	(handPosCPT)
       endobserve
       cost (aware		(no	(0.2))
				(yes	(0.8)))
endaction
reward	(planstep	(a	(0.0))
			(b	(0.2))
			(c	(0.2))
			(d	(0.2))
			(e	(0.2))
			(g	(0.2))
			(h	(0.2))
			(j	(1.0))
			(k	(20.0)))
discount 0.9
//horizon 1000
tolerance 0.001