Scribd
Upload
63 views21 pages

Intelligent Agent: Definition: An Intelligent Agent Perceives Its Environment Via

An intelligent agent perceives its environment through sensors and acts rationally through actuators. It can be implemented through an agent program that maps percepts to actions while updating its internal state. The ideal agent always chooses actions that maximize its performance given the task environment, which includes the performance measure, environment properties, available actions, and sensors. Agent architectures can range from simple reflex agents to more complex goal-based or utility-based agents. The most challenging environments for agents are those that are inaccessible, non-deterministic, dynamic, and continuous.

Uploaded by

ali hussain
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
63 views21 pages

Intelligent Agent: Definition: An Intelligent Agent Perceives Its Environment Via

An intelligent agent perceives its environment through sensors and acts rationally through actuators. It can be implemented through an agent program that maps percepts to actions while updating its internal state. The ideal agent always chooses actions that maximize its performance given the task environment, which includes the performance measure, environment properties, available actions, and sensors. Agent architectures can range from simple reflex agents to more complex goal-based or utility-based agents. The most challenging environments for agents are those that are inaccessible, non-deterministic, dynamic, and continuous.

Uploaded by

ali hussain
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
You are on page 1/ 21

Intelligent Agent

Definition: An intelligent agent perceives its environment via


sensors and acts rationally upon that environment with its
actuators.
Humans

Sensors:
􀂄 Eyes (vision), ears (hearing), skin (touch), tongue
(gustation), nose (olfaction), neuromuscular system
(proprioception)
Percepts:
􀂄 At the lowest level – electrical signals
􀂄 After preprocessing – objects in the visual field (location,
textures, colors, …), auditory streams (pitch, loudness,
direction), …
Actuators: limbs, digits, eyes, tongue, …
Actions: lift a finger, turn left, walk, run, carry an
object, …
Notion of an Artificial Agent
Vacuum Cleaner World

Percepts: location and contents, e.g. [A, Dirty]


Actions: Left, Right, Suck, NoOp
Vacuum Agent Function
Rational Agent
What is rational depends on:
􀂄 Performance measure - The performance
measure that defines the criterion of success
􀂄
Environment - The agents prior knowledge of the
environment
􀂄
Actuators - The actions that the agent can perform
􀂄
Sensors - The agent’s percept sequence to date

We’ll call all this the Task Environment (PEAS)


Vacuum Agent PEAS

Performance Measure: minimize energy


consumption, maximize dirt pick up. Making this
precise: one point for each clean square over
lifetime of 1000 steps.
Environment: two squares, dirt distribution
unknown, assume actions are deterministic and
environment is static (clean squares stay clean)
Actuators: Left, Right, Suck, NoOp
Sensors: agent can perceive it’s location and
whether location is dirty
Automated taxi driving system
Performance Measure: Maintain safety, reach
destination, maximize profits (fuel, tire wear),
obey laws, provide passenger comfort, …
Environment: U.S. urban streets, freeways,
traffic, pedestrians, weather, customers, …
Actuators: Steer, accelerate, brake, horn,
speak/display, …
Sensors: Video, sonar, speedometer,
odometer, engine sensors, keyboard input,
microphone, GPS, …
Autonomy

A system is autonomous to the extent that its


own behavior is determined by its own
experience.

Therefore, a system is not autonomous if it is


guided by its designer according to a priori
decisions.
To survive, agents must have:
􀂄 Enough built-in knowledge to survive.
􀂄 The ability to learn.
Properties of Environments

Fully Observable/Partially Observable


􀂄 If an agent’s sensors give it access to the complete state
of the environment needed to choose an action, the
environment is fully observable.
􀂄 Such environments are convenient, since the agent is
freed from the task of keeping track of the changes in the
environment.

Deterministic
􀂄 An environment is deterministic if the next state of the
environment is completely determined by the current state of
the environment and the action of the agent.
􀂄 In an accessible and deterministic environment, the agent
need not deal with uncertainty.
Properties of Environments

Static/Dynamic.
􀂄 A static environment does not change while the
agent is thinking.
􀂄 􀂄 The agent doesn’t need to observe the world during
deliberation.

Discrete/Continuous.
􀂄 If the number of distinct percepts and actions is
limited, the environment is discrete, otherwise it is
continuous.
Environment Characteristics
Some agent types
(1) Table-driven agents
􀂄 use a percept sequence/action table in memory to find the next
action. They are implemented by a (large) lookup table.

(2) Simple reflex agents


􀂄 are based on condition-action rules, implemented with an
appropriate production system. They are stateless devices which
do not have memory of past world states.

(3) Model-based reflex agents


􀂄 have internal state, which is used to keep track of past states
of the world.

(4) Goal-based agents


􀂄 are agents that, in addition to state information, have goal
information that describes desirable situations. Agents of this
kind take future events into consideration.

(5) Utility-based agents


􀂄 base their decisions on classic axiomatic utility theory in
order to act rationally.
Table-driven/reflex agent architecture
Simple Vacuum Reflex Agent

function Vacuum-Agent([location,status])
returns Action
if status = Dirty then return Suck
else if location = A then return Right
else if location = B then return Left
Model-based agent architecture
Architecture for goal-based agent
Architecture for a complete utility-based agent
Summary: Agents

An agent perceives and acts in an environment, has an architecture,


and is implemented by an agent program.
Task environment – PEAS (Performance, Environment, Actuators,
Sensors)

An ideal agent always chooses the action which maximizes its expected
performance, given its percept sequence so far.

An autonomous agent uses its own experience rather than built-in


knowledge of the environment by the designer.

An agent program maps from percept to action and updates internal


state.
􀂄
Reflex agents respond immediately to percepts.
􀂄 Goal-based agents act in order to achieve their goal(s).
􀂄 Utility-based agents maximize their own utility function.
Representing knowledge is important for successful agent design.

The most challenging environments are inaccessible, nondeterministic,


dynamic, and continuous
Thank You For
Listening

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy