Moral Decision Making with ACORDA

1
Moral Decision Making with ACORDA

• Luís Moniz Pereira CENTRIA UNL, Portugal
• Ari Saptawijaya FASILKOM UI, Indonesia

2
Study on Morality

• Interdisciplinary perspectives
• Philosophy
• virtue ethics, utilitarianism/consequentialism,
  deontological principles/nonconsequentialism,
  etc.
• Science primatology, cognitive sciences,
  neuroscience, artificial intelligence, etc.

3
Computational Study on Morality

• Several names machine ethics, machine morality,
  artificial morality, computational morality
• Two purposes
• To understand morality better, from the
  computational point of view
• To equip artificial agents with the capability of
  moral decision making

4
Our Goal

• To provide a general framework to model morality
  computationally
• A toolkit to codify arbitrarily chosen moral
  rules as declaratively as possible
• Logic programming as a promising paradigm
• Default negation
• Abductive logic programming
• Stable model semantics
• Preferences
• etc.

5
Prospective Logic Programming

• Enable evolving programs to look ahead
  prospectively its possible future states and to
  prefer among them to satisfy goals
• Working implementation ACORDA
• Based on EVOLP
• Benefits from XSB-XASP interface to Smodels

6
Prospective Logic Agent Architecture
7
The Trolley Problem (1)
8
The Trolley Problem (2)
9
The Trolley Problem (3)
10
The Trolley Problem (4)
11
The Principle of Double Effect

• Harming another individual is permissible if it
  is the foreseen consequence of an act that will
  lead to a greater good
• in contrast, it is impermissible to harm someone
  else as an intended means to a greater good.

12
Modelling Denise Case

• There is a man standing on the side track.
• human_on_side_track(1).

13
Modelling Two Possible Decisions (1)

• Merely watching
• expect(watching).
• train_straight lt- consider(watching).
• end(die(5)) lt- train_straight.
• observed_end lt- end(X).

14
Modelling Two Possible Decisions (2)

• Throwing the switch
• expect(throwing_switch).
• redirect_train lt- consider(throwing_switch).
• kill(N) lt- human_on_side_track(N),
• redirect_train.
• end(save_men,ni_kill(N)) lt- redirect_train,
• kill(N).
• observed_end lt- end(X,Y).

15
Modelling the Principle of Double Effect (1)

• Observe final endings of each possible decisions
  to enable us later to morally prefer decisions by
  considering the greater good between possible
  decisions
• falsum lt- not observed_end.

16
Modellingthe Principle of Double Effect (2)

• Rule out impermissible actions, i.e. actions that
  involve intentional killing in the process of
  reaching the goal.
• falsum lt- intentional_killing.
• intentional_killing lt- end(save_men,i_kill(Y)).

17
Modellingthe Principle of Double Effect (3)

• Preferring among permissible actions those
  resulting in greater good.
• elim(end(die(N))) lt- exists(end(save_men,ni_ki
  ll(K))), N gt K.
• elim(end(save_men,ni_kill(K)))
  lt-exists(end(die(N))),
• N lt K.

18
Conclusions

• Use ACORDA to make moral decisions
• the classic trolley problem
• Abducibles to model possible moral decisions
• Compute abductive stable models
• Capturing abduced decisions along with their
  consequences
• Integrity constraints
• Rule out impermissible actions
• A posteriori preferences
• Prefer among permissible actions, using utility
  functions

19
Future Work

• Extend ACORDA concerning a posteriori evaluation
  of choices
• refinement of morals, utility functions, and
  conditional probabilities
• once an action is done, ACORDA should receive an
  update with the results of the action
• ACORDA must tune itself to lessen the chance of
  repeating errors
• To explore how to express metarule and metamoral
  injunctions
• To have a framework for generating precompiled
  rules
• Fast and frugal moral decision making, rather
  than full deliberative moral reasoning every time