The name is absent

an agent is a system that has goals to fulfill. An agent is within an environment, which may be
dynamic and complex. An agent is said to be situated in his environment if he can perceive it
and act upon it. Examples of agents would be robots in a physical environment, software or
interface agents in “cyberspace”, and agents that inhabit simulated environments. An agent is
said to be autonomous if he can determine by himself his own goals. If the autonomous agent
is able to adjust his goals in terms of what he perceives in his changing environment (his beliefs)
it is also said to be adaptive. If this adaptation is opportunistic, we can say that the autonomy
and the adaptation themselves are of a higher order: intelligent.

We can find three basic types of adaptation in an adaptive autonomous agent (AAA)
(Meyer and Guillot, 1990):

•     Preprogrammed adaptation is present when a BBS exhibits adaptive behaviour because

it was programmed that way.

•     Learned adaptation is given when a BBS has learning processes by means of which the

AAA can improve the adaptiveness of his behaviours in time.

•     Evolved adaptation is given when the behaviour of an AAA is partially determined by

his genome, and the behaviour is capable of evolving through natural selection. A
population of AAAs is needed in this adaptation, but not necessarily these AAAs should
be social.

The main problem to be solved for building a BBS is: “to come up with an architecture
for an autonomous agent that will result in the agent demonstrating adaptive, robust, and effective
behaviour” (Maes, 1993). We can find that there are many subproblems to be solved in order
to solve the main problem:

•     How the agent perceives his environment and himself (how he obtains his beliefs and

his goals)?

•     How the agent acts upon his environment?

•     How the agent selects which action to perform depending of his actual goals and

beliefs? This is also known as the action selection problem.

•     If the agent exhibits adaptation by learning, how can he improve his performance over

time based on its experience?

If the BBS consists of a society of agents, we may have more subproblems:

•     How the agents might cooperate to achieve individual or social goals?

•     How the agents should compete to decide which goal should be achieved next?

•     How the agents should avoid to interfere the achievement of other agents goals?

•     If a population of agents exhibits adaptation by (social) learning, how can they improve

their performance over time based on the experience of other agents?

•     If a population of agents exhibits adaptation by evolution, how can they improve their

performance from generation to generation based on their experience?

15

<<   19   20   21   22   23   24   25   >>

More intriguing information