Some thoughts on multi-agent systems and "hyper-economy".

Alexander 'Sasha' Chislenko (
Fri, 21 Nov 1997 01:26:32 -0500

I have been interested in multi-agent complex systems lately, and though
I still have to do a lot more reading and thinking, I would like to share a
few ideas; maybe you'll help me figure things out. As always, I am
looking for all kinds of remarks and references.

Multi-agent systems and action spaces

People distinguish various types of systems consisting of relatively
autonomous functional parts. They call them: ecology, economy,
society, organism, software, etc. The rules for identifying these systems
are quite simple. For example, any system consisting of biological
objects would be called an ecology, one made up of humans is a
society, and a part of the latter that has to do with exchanging things is
an economy. However, if one wants to understand the behavior of such
systems (otherwise, why study them?) it seems more productive to
subdivide them into functional types. This also allows to draw analogies
between similar systems of different nature (e.g., a communist economy
may be similar to an integrated organism, as its parts work directly on
the central order, and the role of financial flows are reduced to assist
the economic balancing mechanism. A contract economy looks much
like a forest ecology, except that agents get locked into relationships by
contracts, not niches, and some other manifestations of subsystems'
intelligence. So multi-agent systems can be classified by overall
complexity, internal control methods, structure and viscosity (transport
capacities) of the space, methods of connecting agents into stable
working groups (mutual specialization, physical coupling, force,
emotional affection, ownership, contracts), diversity and intelligence of
agents, etc.

A general theory may also help to predict where new systems may have
features qualitatively different from everything previously observed. For
instance, space within modern communication and computing
environments is effectively non-metric (it takes approximately the same
time and effort to phone anybody in a country, or address any memory
unit within a computer). This means that most space-related laws of all
previous functional spaces would not apply to "digital" systems: there is
no concept of premium location here, or differential rent, no
"reproductive isolation" or other influence of space-induced separation
on agents' communication and diversity. Also digital systems often have
lower replication costs of agents than execution costs, which makes
them dramatically different from all systems more essentially embedded
in their physical substrates. - For humans, it's much easier to translate
an article or to fix an appliance than to transfer their skills to another
human capable. For a computer it is just copying a program.

Together, the above features create a foundation for system design that
is dramatically different from all natural and human agglomerations, in
terms of agent specialization, diversity, and deployment. I would
envision the future intelligence as a collection of highly specialized tools,
with high-bandwidth interconnections, with "personalities", or complex
problem solvers ("achievers", "goal engines", "research tools",
"development threads") consisting of limited contractual relations
between multiple problem-solving, planning, perceiving, and acting
entities, that can at the same time be employed in many other similar
relations. So the entities may use the same "body parts" on a
cooperative or time-sharing basis.

Economy and beyond

Economies are an interesting class of systems. By using quantitative
symbols to represent typical value relations between various resources,
economy allows efficient distribution of signals in the system, and
provides short-sighted selfish agents with incentives to adjust their
consumption and production efforts in accordance with the collective
requirements of all other agents in the system.

Unfortunately, while the economy provides its agents with accurate
estimates of generic values, it has little to offer to each individual agent
in their attempts to figure the value of a certain product to their
particular needs, or offer any other personalized or situational advice.
This kind of knowledge is usually obtained by the economic agents in
about the same way they discovered average social values of common
products and services in pre-economic times: personal experience with
the environment and direct communication with others. There are no
quantitative instruments available for automated processing for this

This is understandable: comprehensive detailed data about each agent's
behavior so far has not been available in a usable form, communication
and computational instruments necessary for processing this data have
not been adequate, transaction costs have been too high, etc. All these
obstacles are now being removed in many systems.

With these tools in place, there appears a foundation for "a second
signalling mechanism" in an economic system: together with conventional
aggregate indicators of average costs of resources and services and
their expectations, the new crop of signalling instruments may deliver
suggestions of expected value that particular agents may derive in their
individual situations from such resources or services. Then agents can
be better equipped to optimize their behavior by using all available
knowledge for comparing personal and global costs, risks, and utilities.

Such systems (I would call them "hyper-economies", or
"super-economies") may be implemented in both completely automated
environments and those involving humans (e.g., they could assist people
in selection of things most appropriate for their tastes and situations,
from recommending movies they want to see, to tools that would satisfy
their needs at the best price to choosing diets and insurance plans for
their own goals and conditions).

There is some analogy here with the notion of "psychohistory"
suggested by Isaac Asimov in his Foundation series, except that instead
of using detailed representations of social processes for long-term
prediction of future events (which is hardly possible with a still very
imperfect model of a huge chaotic system), I suggest a more modest
goal of using them for richer local modelling and adaptive control. The
only advantage here is that this modest goal seems actually achievable.

>From research to development

I know of a very few people working in similar directions. In the current
situation, good theorists work on conceptualizing existing systems, and
are usually not aware of new developments in software that may create
foundation for new systems and theories. On the other hand, people
working on the first versions of new signalling systems usually do not
have much expertise or interest in complex systems analysis, and spend
their efforts debugging and distributing software. As a result, the new
system structures are arising, once again, unconsciously.

I am trying to approach this topic from two sides, with some progress in
both, though I feel it is too premature to write about the details yet.

One, is theoretical considerations of how the new signaling systems may
change our familiar economic notions, such as capital, interest,
efficiency, liquidity, inflation, emission rights, secondary and derivative
instruments. Some of these features will remain relatively unchanged but
become more liquid (faster distribution and lower transaction costs) and
more efficient. Other parameters may turn from scalar to vector or a
more complex structure (e.g., replacement of the numerical
representation of value with a matrix of "value of this object for a
purpose P as estimated by an agent A"). Some features, such as
"situational/detail derivatives" for assessing values and risks of, and
balancing among, particular utilities will be entirely new.

Similar changes will happen with the concepts from social and
ecological fields. Communities do not have to be local anymore, they
may have variable/adaptable geometries, relations between managing
and performing agencies will be redefined, new control structures and
dynamic patterns arise, etc.

At the same time, I am working on simple versions of such systems in
Internet environments, where the data is already available, and the
results seem of direct practical use. I am looking for people who would
be interested in helping me develop architectures and algorithms for
such systems. At this point, I can't pay anybody to work on it, but this
is a very promising field, and it may offer very fine student and research

Among the first applications of this approach I envision large automated
collaborative filtering projects, link exchange programs and targeted
advertising, balancing flows of information in accordance with diverse
and dynamic interests of creators, consumers, providers, and sponsors
of the Web content.

My hope is that eventually such hyper-economic schemes will develop
to store and process increasingly complex representations of agent
interests and utilities, and have a great variety of competing intelligent
algorithms for optimizing system processes, thus turning into a hybrid of
an economic self-regulatory mechanism, complex multi-faceted
community, and distributed artificial intelligence, with secondary data
representation and signalling mechanisms forming emerging
self-awareness of the new systems.


( The latest hypertext version of this article is available at )

Alexander Chislenko <>