1.
Ar#ficial
Agents
Without
Ontological
Access
to
Reality
Olivier
Georgeon
h8p://liris.cnrs.fr/ideal/mooc
h8p://liris.cnrs.fr/ideal/mooc
1/31

2.
Defini#ons
• Ontology:
“Onto”
(to
be)
+
“Logos”
(discourse):
– Discourse
on
what
“is”.
• Agent
without
ontological
access
to
reality:
– Agent
that
don’t
have
access
to
what
“is”
in
reality.
– Agent
whose
input
data
is
NOT
a
representa5on
of
reality.
• We
do
not
consider
input
data
as
the
agent’s
percep#on…
• …
then
input
data
should
be
considered
as
what?
h8p://liris.cnrs.fr/ideal/mooc
2/31

3.
Mainstream
philosophy/epistemology
• Philosophy
– Kant
:
Cogni#ve
agent’s
don’t
have
access
to
reality
“as
such”
(noumenal
reality).
• Psychology
– Findlay
&
Gilchrist
(2003).
Ac#ve
Vision.
• Cogni#ve
Science.
– “Percep#on
and
ac#on
arise
together,
dialec#cally
forming
each
other”
(Clancey,
1992,
p5).
• Construc#vist
epistemology
– Piaget:
Percep#on
and
ac#on
are
inseparable
(sensorimotor
schemes).
• Even
quantum
physics?
– Predicts
results
of
experiments
without
assuming
an
objec#ve
state
of
reality
(talking
about
the
state
of
Schrödinger’s
cat
makes
no
sense)
h8p://liris.cnrs.fr/ideal/mooc
3/31

4.
Scope
of
this
presenta#on
• Philosophical
prerequisite:
– Cogni5ve
agents
have
no
access
to
reality
“as
such”
• Our
claim:
– Most
BICAs
and
machine
learning
algorithms
have
not
yet
acknowledged
this
philosophy!
• Content
of
the
presenta#on:
– How
can
we
implement
this
philosophy
into
BICAs?
– What
will
we
gain
and
loose
from
doing
so?
h8p://liris.cnrs.fr/ideal/mooc
4/31

5.
The
interac#on
cycle
Agent
Environment
Input
data
Output
data
The
agent
interacts
with
the
environment
by
receiving
input
data
and
sending
output
data.
When
does
the
interac#on
cycle
begin
and
end?
h8p://liris.cnrs.fr/ideal/mooc
5/31

6.
Symbolic
modeling
Agent
Seman&c
rules
Reality
Symbol Action
The
agent
receives
a
symbol
that
matches
seman5c
rules.
There
is
a
predefined
“discourse
on
what
is”
(the
set
of
symbols
and
seman#c
rules)
and
the
agent
has
access
to
it.
The
agent
is
a
passive
observer
of
reality.
The
cycle
begins
with
the
agent
receiving
input
data
and
ends
with
the
agent
sending
output
data.
h8p://liris.cnrs.fr/ideal/mooc
6/31

7.
Reinforcement
learning
Agent
Reality
st
∈ S
Action
at ∈ A
Observation
ot = f (st) ∈ O
Reward
rt = r (st) ∈ ℝ
There
is
a
predefined
“discourse
on
what
is”
(the
set
S).
Most
reinforcement
learning
algorithms
assume
that
the
observa#on
represents
the
state
of
reality
(par#ally
and
with
noise).
The
agent
is
a
passive
observer
of
reality.
The
cycle
begins
with
the
agent
receiving
input
data
and
ends
with
the
agent
sending
output
data.
h8p://liris.cnrs.fr/ideal/mooc
7/31

8.
Experiment
/
Result
cycle
Agent
ExperimentResult
rt ∈ R xt ∈ X
Reality
The
cycle
begins
with
the
agent
sending
output
data
and
ends
with
the
agent
receiving
input
data.
The
agent
is
an
ac#ve
observer
of
reality
(embodiment
paradigm).
h8p://liris.cnrs.fr/ideal/mooc
We
can’t
assume
that
input
data
represent
the
state
of
reality:
it
may
not!
Most
BICAs
and
Machine
learning
algorithms
fail
to
generate
interes#ng
behaviors.
In
a
given
state
of
reality,
rt
varies
depending
on
xt.
8/31

9.
Comparison
h8p://liris.cnrs.fr/ideal/mooc
Agent
Reality
Agent
Reality
a)
Tradi#onal
model
b)
Embodied
model
a)
and
b)
are
mathema#cally
equivalent
but
:
-­‐ a)
highlights
the
common
assump#on
that
input
data
represents
reality.
-­‐ b)
highlights
that
this
assump#on
may
be
wrong.
9/31
it it
ot ot+1

10.
Agents
Without
Ontological
Access
(AWOAs)
are
“indie”
computer
science
• Ar#ficial
Intelligence
(Russell
&
Norvig
2010,
p.
iv).
– ”The
problem
of
AI
is
to
build
agents
that
receive
percepts
from
the
environment
and
perform
ac5ons”
– The
problem
of
AI
is
to
build
agents
that
receive
data
(that
may
not
be
percepts)
from
the
environment
and
make
decisions
(that
may
not
be
ac5ons).
• Reinforcement
learning:
(Su8on
&
Barto
1998,
p.
4).
–
“Clearly,
such
an
agent
must
be
able
to
sense
the
state
of
the
environment
to
some
extent
and
must
be
able
to
take
ac#ons
that
affect
the
state.
The
agent
also
must
have
goals
rela5ng
to
the
state
of
the
environment.”
– The
agent
must
have
preferences
(drives)
that
may
not
relate
to
the
state
of
the
environment
“as
such”.
• AWOAs
relate
to
other
“indie”
approaches
to
AI:
– Enac#on,
embodied
cogni#on,
developmental
learning,
mul#
agent
systems,
etc.
• AWOAs
differ
from
tradi#onal
AI
by
design
rather
than
by
technique
– All
techniques
can
be
used
in
both
ways
(rule
based
systems,
connec#onist,
mul#-­‐
agent
systems,
reinforcement
learning
techniques,
etc.)
h8p://liris.cnrs.fr/ideal/mooc
10/31

11.
Example
(-­‐3)
(-­‐3)
(-­‐1)
(-­‐1)
(5)
(-­‐10)
Set
E
of
6
experiments:
Set
R
of
2
results:
Set
I
=
E
x
R
of
12
interac#ons
(with
valence):
(-­‐1)
(-­‐1)
(-­‐1)
(-­‐1)
0
or
1
h8p://liris.cnrs.fr/ideal/mooc
The
Agent
/
Environment
coupling
affords
hierarchical
regulari#es
of
interac#on,
e.g.,
-­‐
Amer
,
experiment
results
more
likely
in
than
in
.
-­‐
Amer
,
sequence
can
omen
be
enacted.
-­‐
Amer
,
sequence
can
omen
be
enacted.
11/31

12.
The "Little loop problem"
http://liris.cnrs.fr/ideal/mooc
Bump:
Touch:
Move
Forward
or
bump
(5)
(-­‐10)
Turn
lem
/
right
(-­‐3)
Feel
right/
front
/
lem
(-­‐1)
12/31

13.
4.
Afford
Time
6.
Choose
Decision
Time
3.
Ac#vate
5.
Propose
7.
Enact
1.
h8p://liris.cnrs.fr/ideal/mooc
Hierarchical
bo8om-­‐up
sequence
learning
13/31

14.
ExperimentResult
c) Experiment/Result Model
r ∈ R x ∈ X
Agent
Intended
interaction
Enacted
interaction
i = 〈x,r〉 ∈ X×R
d) Interactional Model
Reality
Agent
Reality
e = 〈x,r’〉 ∈ X×R
Interac#onal
model
Embodied models: the agent must use the active capacity of its body to make experiments
in order to learn about reality.
h8p://liris.cnrs.fr/ideal/mooc
14/31

15.
Agent
Environment
Environment “known” at time td
ecd ∈ Cd icd ∈ Cd
ep1 ip1
ipj ∈ Iepj ∈ I
Decisional mechanism
Recursive
learning
and
self-­‐
programming
h8p://liris.cnrs.fr/ideal/mooc
15/31

16.
Ac#vity
analysis
10 20 30 40 50 60 70 80 90 100
100 110 120 130 140 150 160 170 180 190 200
200 210 220 230 240 250 260 270 280 290 300
300 310 320 330 340 350 360 370 380 390 400
touch
front
–
move
forward
(step
74)
70 80 90 100
touch
lem
–
turn
lem
–
move
forward
(Step
186)
40 50 60 70 80 90 100
140 150 160 170 180 190 200
h8p://liris.cnrs.fr/ideal/mooc
16/31

17.
e-­‐puck
robot
(it
resists
to
noise!)
h8p://liris.cnrs.fr/ideal/mooc
17/31

18.
It
allows
training
h8p://liris.cnrs.fr/ideal/mooc
18/31

19.
Rudimentary distal perception
!"#$%!%
!"#$%&%
!"#$%'%
()*+$,%*#-*."/%0#,1%
Detects
rela#ve
displacement
of
objects
and
approximate
direc#on
within
180°
span
(area
A,
B,
or
C).
“Likes”
rapprochement.
“Dislikes”
disappearance.
h8p://liris.cnrs.fr/ideal/mooc
19/31

20.
Self-­‐programming
h8p://liris.cnrs.fr/ideal/mooc
20/31

21.
No
free
lunch
for
machine
learning
• It
does
not
violate
the
“no
free
lunch
theorem”
– Wolpert,
D.H.,
&
Macready,
W.G.
(1997)
• What
we
loose:
– It
does
not
learn
to
reach
predefined
goal
states.
• e.g.,
win
at
chess.
• What
we
gain
– It
learns
hierarchical
sa#sfying
habitudes
much
faster.
– Prac#cal
applica#ons
when
we
need
systems
to
learn
habitudes:
• e.g,
home
automa#on,
somware
adapta#on,
end-­‐user
programming…
– Robots
that
interact
with
the
real
world
(without
predefined
model)
– Theore#cal
applica#ons
• It
opens
the
way
to
higher-­‐level
cogni#on
(if
we
trust
Kant,
Piaget,
etc.)
h8p://liris.cnrs.fr/ideal/mooc
21/31

22.
AImergence
h8p://www.oliviergeorgeon.com/aimergence
h8p://liris.cnrs.fr/ideal/mooc
22/31

23.
Non-­‐Markov
Reinforcement
Learning
Stage 1 Stage 2 Stage 3
40 200 240 320 480 520 640 800 840
-15
-12.5
-10
-7.5
-5
-2.5
0
2.5
o1.a1…
on.an.on+1,
|o1…
on+1∈O
and
a1…
an∈A.
h8p://liris.cnrs.fr/ideal/mooc
23/31

24.
Blue
phenomenon
White
phenomenon
Level
3
Unknown
1
23
4
5
6
1
? ?
10
? ? ? ?
20
? ? ? ? ? ? ?
30
?
40 50 60 70
Time
h8p://liris.cnrs.fr/ideal/mooc
24/31

25.
Agent
Intended
Interaction
Enacted
interaction
i = 〈x,r〉 ∈ X×R
d) Interactional model
Reality
Agent
Intended
experience
Enacted
experience
e ∈ E i ∈ E
e) Experiential model
Reality
e = 〈x,r’〉 ∈ X×R
Experien#al
model
It’s a radical inversion of our viewpoint on artificial agent:
We focus on the agent’s stream of phenomenological experience
1
23
4
5
6
1
? ?
10
? ? ? ?
20
? ? ? ? ? ? ?
30
?
40 50 60 70
h8p://liris.cnrs.fr/ideal/mooc
25/31

26.
Agent
Intended
experiences
I Σ
Enacted
experiences
E Σ
Reality
Spatial
displacement
𝜏
Spatial coupling
Σ : Experiences with spatial attributes
h8p://liris.cnrs.fr/ideal/mooc
26/31

27.
Interac#on
Timeline
Egocentric
Spa#al
Memory
Hierarchical
Sequen#al
System
Behavior
Selec#on
Intend
Propose
Propose
Learn
/
Track
Ontology
Evoke
Construct
Enact
AGENT
h8p://liris.cnrs.fr/ideal/mooc
27/31

28.
Spatial Little Loop Problem
http://liris.cnrs.fr/ideal/mooc
28/31

29.
Dynamic
environment
h8p://liris.cnrs.fr/ideal/mooc
29/31

30.
Robo#cs
research
h8p://liris.cnrs.fr/ideal/mooc
Bumper
tac#le
sensor
Panoramic
camera
Ground
op#c
sensor
h8p://liris.cnrs.fr/simon.gay/index.php?page=eirl&lang=en
30/31

31.
Conclusion:
a
research
approach
• Theory
of
ar#ficial
Agents
Without
Ontological
Access
to
reality
(AWOA)
is
under
development.
• We
design
embodied
models
that
focus
on
the
agent’s
stream
of
phenomenological
experience.
• We
validate
the
agents
through
behavioral
analysis
rather
then
through
performance
measures.
• Create
animal-­‐level
intelligence
before
human-­‐level
intelligence.
– “Animal-­‐level
Turing
test”
based
on
behavioral
analysis?
• We
(as
a
community)
must
define
criteria
of
intelligent
behavior.
• Incremental
approach:
imagine
increasingly
difficult
experiments
and
design
smarter
agents
in
parallel.
– (aimergence
game).
h8p://liris.cnrs.fr/ideal/mooc
31/31