Download Document

Artificial Intelligenceand
Intelligent Agents
LECTURE # 3
Intelligence
Intelligence has been defined in many different ways including as one's
capacity for
Logic
It can be more generally described as
Understanding
the ability to perceive information, and
self-awareness
to retain it as knowledge to be applied
Learning
towards adaptive behaviors within an
 emotional knowledge,
environment or context.
 planning,
 creativity and
 problem solving.
Artificial Intelligence
Artificial intelligence (AI) is intelligence exhibited by machines.
In computer science, an ideal "intelligent" machine is a flexible rational agent that
perceives its environment and takes actions that maximize its chance of success at some
goal.
The term "artificial intelligence" is applied when a machine mimics "cognitive" functions
that humans associate with other human minds, such as "learning" and "problem
solving".
Capabilities currently classified as AI include successfully understanding human speech,
competing at a high level in strategic game systems (such as Chess and Go), self-driving
cars, and interpreting complex data.
 AI research is divided into subfields that focus on specific problems or on
specific approaches or on the use of a particular tool or towards satisfying
particular applications.
Weak AI
Weak AI (also known as narrow AI) is non-sentient artificial intelligence
that is focused on one narrow task.
Weak AI is defined in contrast to either strong AI (a machine with
consciousness, sentience and mind) or artificial general intelligence (a
machine with the ability to apply intelligence to any problem, rather than
just one specific problem).
All currently existing systems considered artificial intelligence of any sort
are weak AI at most.
Example : SIRI
Strong AI
Strong AI is a term used to describe a certain mindset of artificial
intelligence development.
Strong AI's goal is to develop artificial intelligence to the point where the
machine's intellectual capability is functionally equal to a human's.
This approach presents a solution to the problems of symbolic attempts
to create human intelligence in computers.
Strong AI
Instead of trying to give the computer adult-like knowledge from the
outset, the computer would only have to be given the ability to interact
with the environment and the ability to learn from those interactions.
 As time passed it would gain common sense and language on its own.
This paradigm seeks to combine the mind and the body, whereas the
common trend in symbolic programming (i.e. CYC) has been to disregard the
body to the detriment of the computer's intellect.
Neat AI and Scruffy AI
Neat and scruffy are labels for two different types of artificial
intelligence (AI) research.
Neats consider that solutions should be elegant, clear and provably
correct.
Scruffies believe that intelligence is too complicated (or computationally
intractable) to be solved with the sorts of homogeneous system such neat
requirements usually mandate.
Neat AI and Scruffy AI
Much success in AI came from combining neat and scruffy approaches.
For example, there are many cognitive models matching
human psychological data built in Soar and ACT-R.
Both of these systems have formal representations and execution
systems, but the rules put into the systems to create the models are
generated ad hoc.
Soar- Cognitive architecture
The main goal of the Soar project is to be able to handle the full range of
capabilities of an intelligent agent, from highly routine to extremely difficult
open-ended problems.
In order for that to happen, according to the view underlying Soar, it needs
to be able to create representations and use appropriate forms of knowledge
(such as procedural, declarative, episodic).
Soar should then address a collection of mechanisms of the mind.
Also underlying the Soar architecture is the view that a symbolic system is
essential for general intelligence (see brief comment
on neats versus scruffies).
Soar- Cognitive architecture
This is known as the physical symbol system hypothesis. The views of cognition
underlying Soar are tied to the psychological theory expressed in Allen Newell's
book, Unified Theories of Cognition.
While symbol processing remains the core mechanism in the architecture, recent
versions of the theory incorporate non-symbolic representations and processes,
including reinforcement learning, imagery processing, and emotion modeling.
Soar's capabilities have always included a mechanism for creating new
representations, by a process known as "chunking".
Ultimately, Soar's goal is to achieve general intelligence, though this is
acknowledged to be an ambitious and possibly very long-term goal.
Agent
An agent is anything that can be viewed as perceiving its environment
through sensors and acting upon that environment through effectors.
A human agent has eyes, ears, and other organs for sensors, and hands,
legs, mouth, and other body parts for effectors.
A robotic agent substitutes cameras and infrared range finders for the
sensors and various motors for the effectors.
A software agent has encoded bit strings as its percepts and actions.
Agents interact with environments
through sensors and effectors.
How AGENTS SHOULD ACT?
Rationally??
A rational agent is one that does the right thing.
What is rational at any given time depends on four things:
 The performance measure that defines degree of success.
 Everything that the agent has perceived so far. We will call this complete
perceptual history the percept sequence.
 What the agent knows about the environment.
 The actions that the agent can perform.
Ideal rational agent:
For each possible percept sequence, an ideal rational agent should do
whatever action is expected to maximize its performance measure, on
the basis of the evidence provided by the percept sequence and
whatever built-in knowledge the agent has.
The ideal mapping from percept sequences to
actions
 Once we realize that an agent's behavior depends only on its percept
sequence to date, then we can describe any particular agent by making a
table of the action it takes in response to each possible percept sequence.
 Such a list is called a mapping from percept sequences to actions. We can,
in principle, find out which mapping correctly describes an agent by trying
out all possible percept sequences and recording which actions the agent
does in response.
 And if mappings describe agents, then ideal mappings describe ideal
agents. Specifying which action an agent ought to take in response to any
given percept sequence provides a design for an ideal agent.
Autonomy
An agent's behavior can be based on both its own experience and the builtin knowledge used in constructing the agent for the particular environment
in which it operates.
 A system is autonomous to the extent that its behavior is determined by its
own experience.
It would be reasonable to provide an artificial intelligent agent with some
initial knowledge as well as an ability to learn.
A truly autonomous intelligent agent should be able to operate successfully
in a wide variety of environments, given sufficient time to adapt.
STRUCTURE OF INTELLIGENT AGENTS
Agents by describing their behavior—the action that is performed after any
given sequence of percepts.
The job of AI is to design the agent program: a function that implements the
agent mapping from percepts to actions. We assume this program will run on
some sort of computing device, which we will call the architecture.
The architecture might be a plain computer, or it might include specialpurpose hardware for certain tasks, such as processing camera images or
filtering audio input.
STRUCTURE OF INTELLIGENT AGENTS
It might also include software that provides a degree of insulation
between the raw computer and the agent program, so that we can program
at a higher level.
In general, the architecture makes the percepts from the sensors available
to the program, runs the program, and feeds the program's action choices
to the effectors as they are generated. The relationship among agents,
architectures, and programs can be summed up as follows:
agent = architecture + program
Software agents
 Software agents (or software robots or softbots) exist in rich, unlimited
domains. Imagine a softbot designed to fly a flight simulator for a 747.
The simulator is a very detailed, complex environment, and the software
agent must choose from a wide variety of actions in real time.
Or imagine a softbot designed to scan online news sources and show the
interesting items to its customers. To do well, it will need some natural
language processing abilities, it will need to learn what each customer is
interested in, and it will need to dynamically change its plans when, for
example, the connection for one news source crashes or a new one comes
online.
Software agents
Some environments blur the distinction between "real" and "artificial.“
In the ALIVE environment (Maes et al., 1994), software agents are given as percepts a
digitized camera image of a room where a human walks about. The agent processes the
camera image and chooses an action.
The environment also displays the camera image on a large display screen that the human
can watch, and superimposes on the image a computer graphics rendering of the software
agent.
One such image is a cartoon dog, which has been programmed to move toward the human
(unless he points to send the dog away) and to shake hands or jump up eagerly when the
human makes certain gestures.
Agent programs