SelfProgramming:

1
Self-Programming Operationalizing Autonomy
Eric Nivel, Kristinn R. Thorisson Reykjavik
University eric,thorisson_at_ru.is
AGI '09
2
I. Structural Autonomy Self-Programming II.
Ikon Flux a Proto-Architecture
for Self-Programming Systems III. Conclusion
Future Work
3
I. Structural Autonomy Self-Programming The
Challenge To build systems that gt Operate in
real-world environments Rich, unstructured,
real-time, partially specified, significantly
changing. gt Adapt to change with limited human
intervention Adaptation maintain improve
the utility function redefine their own mission
and the means to fulfill it.
Self-modification. gt Learn to modify and extend
themselves Engineers cannot code everything
beforehand complexity barrier.
Self-construction. gt Are aware of (reason
about) whats going on in the world inside
Reason with incomplete knowledge limited
resources1. Self-awareness. gt Encompass a
broad scope A lot of sensors/actuators,
skills, behaviors, etc. A lot of tasks
responsibilities, in a wide variety of situations
and constraints. Scalability and integration
matter. We propose a generative
approach to Architecture evolve the
structure to adapt behaviors 1. Wang P. (2007)
The Logic of Intelligence. In Artificial General
Intelligence. Springer Verlag.
4
I. Structural Autonomy Self-Programming Theory
gt Operational closure (Varela Maturana1).
The structure (an assembly of components)
creates a network of processes that modify the
structure (by producing components and
impacting the metabolism). Metabolism occurs
in a topological domain (space laws for
production and modification). Dissipative
systems organization is maintained despite flows
of energy matter. Interaction with the
environment raises the need for modification of
the behaviors hence of the structure.
gt Semantic closure (Pattee3, Rocha4) The
organization (structures, processes, etc) is
interpreted as instructions to perform the next
evolutionary step. Semantic realization,
e.g. self-preservation. Intentionality.
1. Maturana H. R. and Varela F. J. (1980)
Autopoiesis and Cognition The Realization of the
Living. Boston, MA Reidel 2. Eigen M. and P.
Schuster P. (1979) The Hypercycle A principle
of natural self-organization. Springer, Berlin 3.
Pattee, H. H. (1995) Evolving Self-Reference
Matter, Symbols, and Semantic Closure
Communication and Cognition. Artificial
Intelligence, 12(1-2). 4. Rocha, L. M. (2000).
Syntactic autonomy, cellular automata, and RNA
editing or why self-organization needs symbols
to evolve and how it might evolve them. In
Closure Emergent Organizations and Their
Dynamics. Chandler J.L.R. and G, Van de Vijver
eds. Annals of the New York Academy of Sciences,
901207-223.
Eigens Hypercycle2
5
I. Structural Autonomy Self-Programming Self-Mo
dification gt An informed evolutionary process
of observation and control Planned to
achieve goals relevant to the utility function.
To realize the function and to remain able to
do so. A continuous situation
assessment. gt Fueled by the complexity of the
world (through interaction) Passive mode,
e.g. observing behaviors performing analogy
between the observed entity and the self.
Proactive mode, e.g. other systems communicating
with the self (direct orders, direct transfer of
raw knowldege). gt Constrained by resource
usage Resources are always scarce, choices
have to be made. Handling problems at hand
vs investing CPU for the future. gt Targeted at
goal achievement Meta-goal defined by the
designer. Survival is a sub-goal. gt Not
natural evolution
6
I. Structural Autonomy Self-Programming In
Practice gt Mapping autopoiesis to a
computational substrate Everything is
programming learning modifying existing code
or producing better one planning producing a
plan (program) and a program to execute it
generating a mission producing goals etc.
Component production ? code synthesis.
gt We need additional classes
of objects To support observation control
models, processes goals. To support
abstraction functions, markers. A
reasonable granularity WRT the complexity of the
synthesis rules and semantics. gt Bootstrap
code Initial ontology, models, internal
drives, meta-goals, programming skills, exemplary
behaviors.
7
I. Structural Autonomy Self-Programming Summary
gt A Computational Autonomous System is a
system - Situated, - Performing in
real-time, - Based on and driven by
models, - Operationally and semantically
closed gt The operational closure is a
continuous program/model synthesis process. gt
The semantic closure a continuous process of
observation and control of the synthesis,
that results from the synthesis process. gt
Self-programming is the global process that
implements both the operational semantic
closures From an engineering
perspective a global and never-terminating
process of architectural synthesis
8
II. Ikon Flux Computational Substrate gt
Platform abstraction Implict parallelism,
memory allocation, garbage collection,
distribution, synchronization, load-balancing.
gt Machine-readable code Transparent code.
Stateless, no side-effects. Explicit
operational semantics. Low complexity
(granularity) at the atomic level. gt
Expressivity Functional language. Can
represent equations (1st order) forward
backward chaining. Multiple LOD
pattern-matching. Abstraction functions,
processes, models, states, sub-systems, ...
Dynamic types ontology and its semantics allowed
to change over time. Simulated execution is
supported. gt Simplicity Operators are
polymorphic. Easy to combine structures.
Models are executable no need for 2 // systems
of representation. Ill-formed code fails
gracefully.
9
II. Ikon Flux Executive gt Data-driven
Programs production rules. Both program AND
input data. Object reduction triggered by
pattern-matching. Programs react to ANY
object matching the pattern. Control
values - activation for programs, -
intensity for everything (potential inputs), -
resilience for everything. Programs inject
new code in the system. Growth
counter-balanced by decay. gt Parallel
Execution is step-locked stack-based I/O
polling. Cellular automata, simulation
runs. Finely grained. // search. gt
Reflective The executive injects objects
reflecting - synthesis operations, -
function calls, - resource usage.
Processes captured as reduction graphs and vice
versa. Processes are full-fledged objects.
Causal relations between internal
processes. gt Real-time gt Does not evolve
10
II. Ikon Flux Semantics gt State A stable
regime of operation a process. Of the
self, of the world. From atoms (code
existence) to complex phenomena causal relations
(explicit), temporal recurrence (implicit).
Abstract expressed as a pattern. gt State
space A topological space to represent the
contributions ( or -) of objects to the
achievement of an arbitrary reference process.
Unit time. gt Goal / constraint A set of
regions in the state space. A process not
implemented yet internal drive, a.k.a.
pregnance1,2. Abstract expressed as a
pattern. gt State space dimension IR U
reference process. Contribution of O
distance (time) of O in a reduction graph,
counted from the achievement of the reference
process, e.g. pregnance satisfaction.
Projection is either automatic (performed by the
executive) or programatic (assertive, performed
by the self). gt Saliency Computational
(explicit) high/low contribution toward process
achievement. Geometrical (implicit) idem
for an observation process, e.g. finding
regularities in a audio stream. Saliency
detection has goal semantics. 1. Thom R.
(1972). Structural Stability and Morphogenesis.
Reading, MA W. A. Benjamin. 2. Thom R. (1990).
Semiophysics A Sketch. Redwood City
Addison-Wesley.
11
II. Ikon Flux Semantics (cont.)
Positive contributions
p3
a
c
t1

D
C
A
A
d
t2
p2
d,p3
t4-t1
p0



t3
p0
P
A
c,p2
t4-t2
A
B
t3
p0(A)
P
P
p4
P
t4-t3
a,p0
at t
-
P(A,B)
t4
b,p1
0
p1
p1

a,p4
-(t4-t3)
B
B
p1(B)

b

x
xP(a,b)
Negative contributions
12
II. Ikon Flux Semantics (cont.) gt Control
Control values (int, act) computed for an object
on a root-dimension as functions of its
contributions to processes. Evaluated
against thresholds (intensity activation) ?
binary activation. Define system
configurations. Fast switching between
configurations.
13
II. Ikon Flux Semantics (cont.) gt Coupling
A dimension is an object, projectable on another
dimension (C(P)P C(O)P x C(O)P, O best for
P). Mutually embedded spaces. To
capture/express dependencies between processes.
14
II. Ikon Flux Semantics (cont.) gt Production
of meaning Thoms Semiophysics1 A process
means another whenever it assumes the same
pragmatics on the system. Dynamics
pregnance channelling. Case study Pavlovs
experiment. 1. Thom R.
(1990). Semiophysics A Sketch. Redwood City
Addison-Wesley.
Simplified model for the pregnance hunger
15
II. Ikon Flux Semantics (cont.)
gt Applications Behaviour
conditioning. Modeling of causal
relations. Semiotic memory. ...
Builds a forward model
Updates the model
r
learning
Updates the state space
Simplified model for pregnance chanelling
slnvisual attention
slnauditive attention


audit. attn.
meat in sight
bell rings


Propagate intensities across dimensions (starting
from the pregnance)
16
II. Ikon Flux Organization Forms (exerimental
!) gt Dynamic higher-order structures
Identified / produced / demoted by code external
to the target structure (stems form bootstrap).
Morphogenesis (closures stability) observed
/ controlled in the state space. Dynamic
Architectural Synthesis.
Structure construction
17
II. Ikon Flux Organization Forms (cont.)





Function stable coupling over time of inputs and
effects
18
II. Ikon Flux Organization Forms (cont.)

Organon aggregate of code forming a substrate for
a function




Function stable coupling over time of inputs and
effects
19
II. Ikon Flux Organization Forms (cont.)
Organism aggregate of organons operationally
closed for a (set of) function(s)

Organon aggregate of code forming a substrate for
a function




Function stable coupling over time of inputs and
effects
20
II. Ikon Flux Organization Forms (cont.)
Organism aggregate of organons operationally
closed for a (set of) function(s)
Individual aggregate of functions, organons and
organisms semantically closed for a (set of)
pregnance(s)

Organon aggregate of code forming a substrate for
a function




Function stable coupling over time of inputs and
effects
21
II. Ikon Flux Sub-Systems gt Internal
sub-systems


F0


F1


22
II. Ikon Flux Sub-Systems (cont.) gt Internal
sub-systems Recursive organization forms.
Realize activities of either the self or
entities in the world. Top-down (development
model in the bootstrap). Bottom-up
(emergent, identified/controlled). Can be
allocated dynamically an instance of the
executive. Can be kept away from evolution.
F0
Action / reaction loop
F1
hand-coded
Internal sub-system
slower, modeling or planning - meta
faster, reactive - concrete


F0


F1


23
II. Ikon Flux Sub-Systems (cont.) gt External
sub-systems Aggregates of axiomatic
functions (exogenous code). Side-effects.
Run on separate machines in their native
implementation. Wrapped in a dedicated
translator. The self can attempt to model
external sub-systems. Programmers can help
by injecting causality (command ? outcome).
External sub-systems




Environment


24
II. Ikon Flux Implementation gt Field-testing
Full scale breadth first and progressive
increase in details and complexity. Loki a
crew member in a theatrical production.
Responsible for the whole stage control. - in a
rich, noisy, unstructured environment under
significant change, - to control a complex
machinery, - interacting with people, -
during long time periods (20 days), -
incremental development (learning,
integration), - supervised (rehearsals) and
unsupervised mode (live performances). No
formal evaluation time / pressures gt no
evaluation procedures / benchmarks. gt Current
limitations Still a large amount of manual
labor. No general determinsitic
methods to identify control the formation of
organization forms (ad-hoc code).
25
III. Conclusion Future Work gt An experimental
framework to build strong autonomous systems
Field-tested in real-world conditions.
Theory is realistic. Non-trivial systems can
be built. Full autonomy is still far away
but were really getting closer. gt
Methodological issue formation of higher-order
structures in general deterministic ways
Investigate modeling self-programing using
Goldfarbs Evolutionary Transformation System1.
Ultimate goal to develop an actual
methodology for engineering arbitrary
systems. gt Build more full-scale real-world
systems Control of complex industrial
systems, software intensive systems,
developmental robotics, ... 1.
Goldfarb L., Gay D. (2005) What is a structural
representation? 5th variation, Faculty of
Computer Science, University of New Brunswick,
Tech. Report TR05-175
26
(No Transcript)
27
II. Ikon Flux Execution Model (cont.)
Deep pattern-matching
pgm1 pgm // transitivity of instance relations
spc (sys object mk1 )
(red mk1 pgm
spc in1 (sys (mk.ins object a) mk2 )
(red mk2
pgm
spc in2 (sys (mk.ins a b) int act res
) nil
((nil in2)) )
((nil in1)) )
((nil inj (core (sys (mk.ins
object b) act int res))) )
28
II. Ikon Flux Execution Model (cont.)
System-wide pattern-matching
ifn // detection of 2 arbitrary processes
terminating at the same time spc nil
(( p1 p2) ( ijt1 ijt2)) () spc p1
sys ((pro ) mk1 ) (red mk1
pgm spc (sys
(mk.xet p1 ) ijt1) nil
((nil p1)) ) spc p2 sys
((pro ) mk2 ) (red mk2
pgm spc (sys (mk.xet
p2 ) ijt2) nil
((nil p2)) )