1. Artificial Intelligence and Lisp #4
Decision Trees
Causal Nets (beginning)
Lab Assignment 2b

2. Uses of Decision Trees Making a choice of action (final or tentative)
Classifying a given situation
Identifying the likely effects of a given situation or action
(Using inverse operation) Identifying possible causes of a given situation

3. A simple example a b b c c c c red green blue white white red green

4. A simple example terms, features outcomes a b b c c c c red green blue
white
white
red
green
blue
outcomes

5. Evaluation of the decision tree
true a
false b b
true c c c c
red
green
blue
white
white
red
green
blue
There will be five variations on this simple theme

6. Notation for the decision tree
{[: a true][: b false][: c true]} a b b c c c c
red
green
blue
white
white
red
green
blue
[a? [b? [c? red green]
[c? blue white]]
[b? [c? white red]
[c? green blue]]]

7. Notation for the decision tree
{[: a true][: b false][: c true]}
[a? [b? [c? red green]
[c? blue white]]
[b? [c? white red]
[c? green blue]]]
Range of a is <true false>, for b and c similarly.
Range ordering may be specified explicitly like here, or implicitly
e.g. if the range is a finite set of integers, but it must be
specified somehow.
Different terms may have different range. It is not necessary
that decision elements on the same level use the same term.
Continuous range is also possible (but little covered here). RR

8. Probabilities in term assignments
[: c true]} same as < >
Range of a is <true false>, for b and c similarly.
[a? [b? [c? red green]
[c? green white]]
[b? [c? white red]
[c? green blue]]] RR
0.585 red
0.315 white
0.100 green
Evaluation: 0.65 * 0.90 red, 0.65 * 0.10 green,
0.35 * 0.90 white, 0.35 * 0.10 green

9. Expected outcome {[: a <0.65 0.35>] [: b <0.90 0.10>]
[: c true]} same as < >
Range of a is <true false>, for b and c similarly.
[a? [b? [c? red green]
[c? green white]]
[b? [c? white red]
[c? green blue]]] RR
0.585 red
0.315 white
0.100 green
Evaluation: 0.65 * 0.90 red, 0.65 * 0.10 green,
0.35 * 0.90 white, 0.35 * 0.10 green
Assign values to outcomes: red , white 4.000, green
(or put these values directly into the tree instead of the colors)
Expected outcome: = 9.610

10. Probabilities in terminal elements
[: c true]} same as < >
Range of a is <true false>, for b and c similarly.
[a? [b? [c? red green]
[c? green white]]
[b? [c? < > red]
[c? green blue]]]
Ordering of value domain is <red white green blue> RR
Eval: * 0.90 red,
0.65 * 0.10 green,
0.35 * 0.90 * < >
0.35 * 0.10 green
red
white
green
blue

11. Hierarchical decision trees
grey subtree b c c c c
red
green
blue
white
white
red
green
blue b d e
true
false
false
true

12. Notation for hierarchical dec. trees
[?[a? [b? [c? red blue]
[c? blue white]]
[b? [c? white red]
[c? red blue] ]]
[d? red-rose poppy pelargonia]
[d? bluebell forget-me-not violet]
[d? waterlily lily-of-the-valley
white-rose]
:range <red blue white> ]
specifies range order
for subtree

13. Expansion of hierarchical dec. trees
[?[a? [b? [c? red blue]
[c? blue white]]
[b? [c? white red]
[c? red blue] ]]
[d? red-rose poppy pelargonia]
[d? bluebell forget-me-not violet]
[d? waterlily lily-of-the-valley white-rose]
:range <red blue white> ]
[?[a? [b? [c? [d? red-rose poppy pelargonia] blue]
[c? blue white]]
[b? [c? white [d? red-rose poppy pelargonia]]
[c? [d? red-rose poppy pelargonia] blue] ]]
[d? red-rose poppy pelargonia]
[d? bluebell forget-me-not violet]
[d? waterlily lily-of-the-valley white-rose]
:range <red blue white> ]

14. Partial evaluation of decision tree
{[: a true][: c true]}
[a? [b? [c? red green]
[c? blue white]]
[b? [c? white red]
[c? green blue]]]
Range of a is <true false>, for b and c similarly. RR
Value of b is not available -- partial evaluation is a way out:
[b? red blue]

15. Partial evaluation of decision tree with term probabilities and expected outcome
{[: a < >][: c true]}
[a? [b? [c? red green]
[c? blue white]]
[b? [c? white red]
[c? green blue]]]
Range of a is <true false>, for b and c similarly
Value of b is not available -- partial evaluation is a way out:
[b? red blue]
Assign values to outcomes:
red , white 4.000, green ,
blue
obtaining [b? ] RR

16. Summary of variations
Basic decision tree with definite (no probabilities) assignments of values
Probabilistic assignments to terms (features)
Continuous-valued outcome, expected outcome
Probabilistic assignments to terminal nodes
Hierarchical decision trees
Incomplete assignments to terms, suggesting partial evaluation
Combinations of these are also possible!

17. Operations on decision trees
Plain evaluation
Partial evaluation
Inverse evaluation
Reorganization (for more efficient interpretation)
Acquisition: obtaining the discrete structure from reliable sources
Learning: using a training set of expected outcomes to adjust probabilities in the tree
Combining with other techniques, e.g. logic- based ones

18. Decision trees in real life
In user manuals: error identification in cars, household machines, etc.
'User help' in software systems
Telephone exchanges
Botanic schemata
Commercial decision making: insurance, finance

19. Decision trees in A.I. and robotics
Current situation described as features/values
From current situation to suggested action(s) (for immediate execution, or to be checked out)
From current situation to extension of it (i.e., additional features/values)
From current situation to predicted future situation (causal reasoning)
From current situation to inferred earlier situation (reverse causal reasoning)(direct or inverse evaluation)
From inferred future or past situation, to action(s)
Learning is important for artificial intelligence

20. Causal Nets A causal net consists of: A set of independent terms
A partially ordered set of dependent terms
An assignment of a dependency expression to each dependent term. (These may be decision trees)
The dependency expression for a term may use independent terms, and also dependent terms that are lower than the term at hand This means the dependency graph is not cyclic.

21. An example (due to Eugene Charniak)
When my wife leaves home, she often (not always) turns on the outside light
She may also turn it on when she expects a guest
When nobody is home, the dog is often outside
If the dog has stomach troubles, it is also often left outside
If the dog is outside, I will probably hear it barking when I approach home
However, possibly it does not bark, and possibly I hear another dog and think it's mine
Problem: given the information I obtain when I approach the house, what is the likelyhood of my wife being at home?

22. Decision trees for dependent terms
lights-are-on [noone-home? <70 30> <20 80>]
dog-outside [noone-home?
[dog-sick? <80 20> <70 30>]
[dog-sick? <70 30> <30 70>] ]
I-hear-dog [dog-outside? <80 20> <10 90>]
Independent terms: noone-home, dog-sick
Dependent terms:
ligths-are-on, dog-outside < I-hear-dog
Notation: integers represent percentages, 70 ~ 0.70
Interpretation: if no-one is home, then 70% chance that outside lights are on, 30% that they are not. If someone is home then 20% and 80% chance, respectively.

23. Decision trees, concise notation
lights-are-on [noone-home? <70 30> <20 80>]
dog-outside [noone-home?
[dog-sick? <80 20> <70 30>]
[dog-sick? <70 30> <30 70>] ]
I-hear-dog [dog-outside? <80 20> <10 90>]
lights-are-on [noone-home? 70% 20%]
[dog-sick? 80% 70%]
[dog-sick? 70% 30%] ]
I-hear-dog [dog-outside? 80% 10%]

24. Causal net using decision trees
lights-are-on [noone-home? 70% 20%]
dog-outside [noone-home?
[dog-sick? 80% 70%]
[dog-sick? 70% 30%] ]
I-hear-dog [dog-outside? 80% 10%]
This is simply a hierarchical causal net with probabilities in the terminal nodes!
If the value assignments for noone-home and dog-sick are given, we can calculate the probabilities for the dependent variables. However, it is the inverse operation that we want.

25. Inverse operation Consider this simple case first:
lights-are-on [noone-home? <70 30> <20 80>]
If it is known that lights-are-on is true,
what is the probability for noone-home ?
Possible combinations:
lights-are-on
noone-home
false
Suppose noone-home is true in 20% of overall cases, obtain:
noone-home
false
Given lights-are-on, noone-home has 14/30 = 46.7%
probability.

26. Inverse operation This will be continued at the next lecture
Read these slides (from the course webpage) and the associated lecture note before that lecture (especially if you are not so familiar with probability theory)

27. Lab 2: Defining a Zoo Miniworld
Milestone 1: static structure in the zoo world
Milestone 2: defining actions in the zoo world, defining rules for precondition resolution, and seeing these rules in operation.
What to do for the lab:
Download and install the lab
Import a few files from milestone 1 of lab 2
Complete the file zoo-actions with action defs
Complete the file zoosim-advise with precond rules
Test-run these and return logs of successful runs

28. What to do - 1 Download and install the lab - like for milestone 1
Import a few files from milestone 1 of lab 2 - see lab instructions (course website + files included in the download)

29. What to do - 2
Complete the file zoo-actions with action definitions, e.g.
-- birthday
[: type verb]
[: latest-rearchived nil]
@Verbdef
[Do .t [birthday .a]] =
[if (not [H- .t (the: .a has-age) nil])
[soact [H! .t (the: .a has-age)
(+ 1 (cv (the: .a has-age))) ]]
[coact]]
Exampl

30. What to do - 3
Complete the file zoosim-advise with precond rules, e.g.
(but this is a 'cheating' rule, not to be used in your final solution to the assignment)
-- precond-rules
[: type entity]
[: latest-rearchived nil]
@Rules
[to-achieve [H- now (the: .a .p) .v]
[fput :a .a :f .p :v .v]
:when [equal (get .a type) animal] ]

31. What to do - 4 Test-run these and return logs of successful runs
Use the 'episode' concept - each episode is a log of successive interactions, command executions, etc.
Work with your own episodes, then isolate the successful steps and do them again in fresh episodes containing as few extra steps as possible
Transfer successful episodes to the ef zoo2report, and upload.

32. This was all for today! Don't forget to read the slides and the lecture note, besides doing the lab!