SlideShare uma empresa Scribd logo
1 de 34
Instructional Objective
 Define an agent
 Define an Intelligent agent
 Define a Rational agent
 Discuss different types of environment
 Explain classes of intelligent agents
 Applications of Intelligent agent
Agents
 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.
Agent and Environment
Agents
 Operate in an environment.
 Perceives its environment through
sensors.
 Acts upon its environment through
actuators/effectors.
 Have goals.
Sensors & Effectors
 An agent Perceives its environment
through sensors.
 The complete set of inputs at a given time
is called percept.
 The current percept, or a sequence of
percepts can influence the actions of an
agent.
Sensors & Effectors
 It can change the environment through
effectors.
 An operation involving an actuator is
called an action.
 Actions can be grouped in to action
sequences.
 So an agent program implement
mapping from percept sequences to
actions.
Agents
 Autonomous Agent: Decide autonomously
which action to take in the current situation
to maximize progress towards its goals.
 Performance measure: An objective
criterion for success of an agent's behavior.
 E.g., performance measure of a vacuum-
cleaner agent could be amount of dirt
cleaned up, amount of time taken, amount
of electricity consumed, amount of noise
generated, etc.
Examples of agents
 Humans
eyes, ears, skin, taste buds, etc. for Sensors.
hands, fingers, legs, mouth for effectors.
 Robots
camera, infrared, bumper, etc. for sensors.
grippers, wheels, lights, speakers, etc. for
effectors.
Structure of agents
 A simple agent program can be defined
mathematically as an agent function which
maps every possible precepts sequence to
a possible action the agent can perform.
 F: p*-> A
 the term percept is use to the agent's
perceptional inputs at any given instant.
Intelligent agents
 Fundamental faculties of intelligence
Acting
Sensing
Understanding, Reasoning, learning
 In order to act you must sense. Blind actions is not
a characterization of intelligence.
 Robotics: sensing and acting. Understanding not
necessary.
 Sensing needs understanding to be useful.
Intelligent Agents
 Intelligent Agent:
must sense,
must act,
must be autonomous(to some extent)
must be rational.
Rational Agent
 AI is about building rational agents.
 An agent is something that perceives
and acts.
 A rational agent always does the right
thing.
What are the functionalities(goals)?
What are the components?
How do we build them?
Rationality
 Perfect Rationality:
Assumes that the rational agent
knows all and will take the action that
maximize the utility.
Human beings do not satisfy this
definition of rationality.
Agent Environment
 Environments in which agents operate
can be defined in different ways.
 It is helpful to view the following
definitions as referring to the way the
environment appears from the point of
view of the agent itself.
Environment: Observability
 Fully Observable: All of the environment
relevant to the action being considered is
observable.
Such environments are convenient, since the
agent is freed from the task of keeping track of
changes in the environment.
 Partially Observable: The relevant features of
the environment are only partially observable.
 Example: Fully obs: Chess; Partially obs: Poker
Environment: Determinism
 Deterministic: The next state of the
environment is completely described by the
current state and the agent’s action. e.g. Image
Analysis
 Stochastic: If an element of interference or
uncertainty occurs then the environment is
stochastic. A partially observable environment will
appear to be stochastic to the agent. e.g. ludo
 Strategic: Environment state wholly determined
by the preceding state and the actions of multiple
agents is called strategic. e.g. Chess
Environment: Episodicity
 Episodic/Sequential:
An Episodic Environment means that
subsequent episodes do not depend on
what actions occurred in previous
episodes.
In a Sequential Environment, the
agent engages in a series of connected
episodes.
Environment: Dynamism
 Static Environment: does not change
from one sate to next while the agent is
considering its course of action. The
only changes to the environment as
those caused by the agent itself.
 Dynamic Environment: Changes over
time independent of the actions of the
agent-and thus if an agent does not
respond in a timely manner, this counts
as a choice to do nothing.
Environment: Continuity
 Discrete/Continuous: If the number of
distinct percepts and actions is limited,
the environment is discrete, otherwise it
is continuous.
Classes of Intelligent Agents
 Intelligent agents are grouped in to five
classes based on their degree of
perceived intelligence and capability.
 Simple reflex agents
 Model based reflex agents
 Goal based agents
 Utility based agents
 Learning agents
Simple reflex agents
 Simple reflex agents act only on the basis of the
current percept, ignoring the rest of the percept
history. The agent function is based on the
condition-action rule: if condition then action.
 Succeeds when the environment is fully
observable.
 Some reflex agents can also contain information
on their current state which allows them to
disregard conditions.
Simple reflex agents
Model based reflex agents
 A model-based agent can handle a partially
observable environment.
 Its current state is stored inside the agent
maintaining some kind of structure which
describes the part of the world which cannot be
seen.
 This knowledge about "how the world evolves" is
called a model of the world, hence the name
"model-based agent".
Model based reflex agents
Goal based agents
 Goal-based agents further expand on the
capabilities of the model-based agents, by using
"goal" information.
 Goal information describes situations that are
desirable. This allows the agent a way to choose
among multiple possibilities, selecting the one
which reaches a goal state.
 Search and planning are the subfields of artificial
intelligence devoted to finding action sequences
that achieve the agent's goals.
Goal based agents
Utility based agents
 Goal-based agents only distinguish between goal
states and non-goal states.
 It is possible to define a measure of how desirable
a particular state is. This measure can be obtained
through the use of a utility function which maps a
state to a measure of the utility of the state.
 A more general performance measure should
allow a comparison of different world states
according to exactly how happy they would make
the agent. The term utility, can be used to describe
how "happy" the agent is.
Utility based agents
Learning agents
 Learning has an advantage that it allows the agents
to initially operate in unknown environments and to
become more competent than its initial knowledge
alone might allow.
 The most important distinction is between the
"learning element", which is responsible for making
improvements, and the "performance element",
which is responsible for selecting external actions.
 The learning element uses feedback from the
"critic" on how the agent is doing and determines
how the performance element should be modified
to do better in the future.
Learning agents
 The last component of the learning
agent is the "problem generator". It is
responsible for suggesting actions that
will lead to new and informative
experiences.
Learning agents
Applications of Intelligent
Agents
 Intelligent agents are applied as
automated online assistants, where they
function to perceive the needs of
customers in order to perform
individualized customer service.
 Use in smart phones in future.
Intelligent agent

Mais conteúdo relacionado

Mais procurados

2-Agents- Artificial Intelligence
2-Agents- Artificial Intelligence2-Agents- Artificial Intelligence
2-Agents- Artificial Intelligence
Mhd Sb
 
Knowledge representation in AI
Knowledge representation in AIKnowledge representation in AI
Knowledge representation in AI
Vishal Singh
 

Mais procurados (20)

Introduction Artificial Intelligence a modern approach by Russel and Norvig 1
Introduction Artificial Intelligence a modern approach by Russel and Norvig 1Introduction Artificial Intelligence a modern approach by Russel and Norvig 1
Introduction Artificial Intelligence a modern approach by Russel and Norvig 1
 
Agents in Artificial intelligence
Agents in Artificial intelligence Agents in Artificial intelligence
Agents in Artificial intelligence
 
AI: AI & Searching
AI: AI & SearchingAI: AI & Searching
AI: AI & Searching
 
AI Agents, Agents in Artificial Intelligence
AI Agents, Agents in Artificial IntelligenceAI Agents, Agents in Artificial Intelligence
AI Agents, Agents in Artificial Intelligence
 
Lecture 2 agent and environment
Lecture 2   agent and environmentLecture 2   agent and environment
Lecture 2 agent and environment
 
AI Lecture 3 (solving problems by searching)
AI Lecture 3 (solving problems by searching)AI Lecture 3 (solving problems by searching)
AI Lecture 3 (solving problems by searching)
 
Agents1
Agents1Agents1
Agents1
 
AI: AI & Problem Solving
AI: AI & Problem SolvingAI: AI & Problem Solving
AI: AI & Problem Solving
 
Agents_AI.ppt
Agents_AI.pptAgents_AI.ppt
Agents_AI.ppt
 
Artificial intelligence agents and environment
Artificial intelligence agents and environmentArtificial intelligence agents and environment
Artificial intelligence agents and environment
 
2-Agents- Artificial Intelligence
2-Agents- Artificial Intelligence2-Agents- Artificial Intelligence
2-Agents- Artificial Intelligence
 
Knowledge representation In Artificial Intelligence
Knowledge representation In Artificial IntelligenceKnowledge representation In Artificial Intelligence
Knowledge representation In Artificial Intelligence
 
Intelligent agent
Intelligent agent Intelligent agent
Intelligent agent
 
Agent architectures
Agent architecturesAgent architectures
Agent architectures
 
Knowledge representation in AI
Knowledge representation in AIKnowledge representation in AI
Knowledge representation in AI
 
Unit1: Introduction to AI
Unit1: Introduction to AIUnit1: Introduction to AI
Unit1: Introduction to AI
 
Problem solving agents
Problem solving agentsProblem solving agents
Problem solving agents
 
AI local search
AI local searchAI local search
AI local search
 
The structure of agents
The structure of agentsThe structure of agents
The structure of agents
 
AI
AIAI
AI
 

Destaque (10)

Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
Ch 2 what is software quality
Ch 2 what is software qualityCh 2 what is software quality
Ch 2 what is software quality
 
Nonparametric statistics
Nonparametric statisticsNonparametric statistics
Nonparametric statistics
 
non parametric statistics
non parametric statisticsnon parametric statistics
non parametric statistics
 
AI: Planning and AI
AI: Planning and AIAI: Planning and AI
AI: Planning and AI
 
AI: Learning in AI
AI: Learning in AI AI: Learning in AI
AI: Learning in AI
 
Planning
PlanningPlanning
Planning
 
Non-Parametric Tests
Non-Parametric TestsNon-Parametric Tests
Non-Parametric Tests
 
Non parametric tests
Non parametric testsNon parametric tests
Non parametric tests
 
Artificial Intelligence Presentation
Artificial Intelligence PresentationArtificial Intelligence Presentation
Artificial Intelligence Presentation
 

Semelhante a Intelligent agent

introduction to inteligent IntelligentAgent.ppt
introduction to inteligent IntelligentAgent.pptintroduction to inteligent IntelligentAgent.ppt
introduction to inteligent IntelligentAgent.ppt
dejene3
 
Jarrar.lecture notes.aai.2011s.ch2.intelligentagents
Jarrar.lecture notes.aai.2011s.ch2.intelligentagentsJarrar.lecture notes.aai.2011s.ch2.intelligentagents
Jarrar.lecture notes.aai.2011s.ch2.intelligentagents
PalGov
 
Jarrar.lecture notes.aai.2011s.ch2.intelligentagents
Jarrar.lecture notes.aai.2011s.ch2.intelligentagentsJarrar.lecture notes.aai.2011s.ch2.intelligentagents
Jarrar.lecture notes.aai.2011s.ch2.intelligentagents
PalGov
 
Rational Agent.pptx
Rational Agent.pptxRational Agent.pptx
Rational Agent.pptx
suchita74
 
Unit 4 Artificial Intelligent Agent.pptx
Unit 4 Artificial Intelligent Agent.pptxUnit 4 Artificial Intelligent Agent.pptx
Unit 4 Artificial Intelligent Agent.pptx
ssuser40ae5e
 

Semelhante a Intelligent agent (20)

intelligentagent-190406015753.pptx
intelligentagent-190406015753.pptxintelligentagent-190406015753.pptx
intelligentagent-190406015753.pptx
 
AI - Agents & Environments
AI - Agents & EnvironmentsAI - Agents & Environments
AI - Agents & Environments
 
introduction to inteligent IntelligentAgent.ppt
introduction to inteligent IntelligentAgent.pptintroduction to inteligent IntelligentAgent.ppt
introduction to inteligent IntelligentAgent.ppt
 
AI_02_Intelligent Agents.pptx
AI_02_Intelligent Agents.pptxAI_02_Intelligent Agents.pptx
AI_02_Intelligent Agents.pptx
 
AI Lesson 02
AI Lesson 02AI Lesson 02
AI Lesson 02
 
Lecture 2 Agents.pptx
Lecture 2 Agents.pptxLecture 2 Agents.pptx
Lecture 2 Agents.pptx
 
Artificial intelligence(03)
Artificial intelligence(03)Artificial intelligence(03)
Artificial intelligence(03)
 
Detail about agent with it's types in AI
Detail about agent with it's types in AI Detail about agent with it's types in AI
Detail about agent with it's types in AI
 
1.1 What are Agent and Environment.pptx
1.1 What are Agent and Environment.pptx1.1 What are Agent and Environment.pptx
1.1 What are Agent and Environment.pptx
 
Lecture 04 intelligent agents
Lecture 04 intelligent agentsLecture 04 intelligent agents
Lecture 04 intelligent agents
 
Jarrar.lecture notes.aai.2011s.ch2.intelligentagents
Jarrar.lecture notes.aai.2011s.ch2.intelligentagentsJarrar.lecture notes.aai.2011s.ch2.intelligentagents
Jarrar.lecture notes.aai.2011s.ch2.intelligentagents
 
Jarrar.lecture notes.aai.2011s.ch2.intelligentagents
Jarrar.lecture notes.aai.2011s.ch2.intelligentagentsJarrar.lecture notes.aai.2011s.ch2.intelligentagents
Jarrar.lecture notes.aai.2011s.ch2.intelligentagents
 
Topic 1 lecture 1
Topic 1 lecture 1Topic 1 lecture 1
Topic 1 lecture 1
 
Lecture 4 (1).pptx
Lecture 4 (1).pptxLecture 4 (1).pptx
Lecture 4 (1).pptx
 
Week 2.pdf
Week 2.pdfWeek 2.pdf
Week 2.pdf
 
Agents(1).ppt
Agents(1).pptAgents(1).ppt
Agents(1).ppt
 
Rational Agent.pptx
Rational Agent.pptxRational Agent.pptx
Rational Agent.pptx
 
Slide01 - Intelligent Agents.ppt
Slide01 - Intelligent Agents.pptSlide01 - Intelligent Agents.ppt
Slide01 - Intelligent Agents.ppt
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
Unit 4 Artificial Intelligent Agent.pptx
Unit 4 Artificial Intelligent Agent.pptxUnit 4 Artificial Intelligent Agent.pptx
Unit 4 Artificial Intelligent Agent.pptx
 

Último

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 

Último (20)

Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024Manulife - Insurer Innovation Award 2024
Manulife - Insurer Innovation Award 2024
 
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
Apidays New York 2024 - The Good, the Bad and the Governed by David O'Neill, ...
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
Deploy with confidence: VMware Cloud Foundation 5.1 on next gen Dell PowerEdg...
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
Bajaj Allianz Life Insurance Company - Insurer Innovation Award 2024
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
HTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation StrategiesHTML Injection Attacks: Impact and Mitigation Strategies
HTML Injection Attacks: Impact and Mitigation Strategies
 
Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...Apidays New York 2024 - The value of a flexible API Management solution for O...
Apidays New York 2024 - The value of a flexible API Management solution for O...
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 

Intelligent agent

  • 1.
  • 2. Instructional Objective  Define an agent  Define an Intelligent agent  Define a Rational agent  Discuss different types of environment  Explain classes of intelligent agents  Applications of Intelligent agent
  • 3. Agents  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.
  • 5. Agents  Operate in an environment.  Perceives its environment through sensors.  Acts upon its environment through actuators/effectors.  Have goals.
  • 6. Sensors & Effectors  An agent Perceives its environment through sensors.  The complete set of inputs at a given time is called percept.  The current percept, or a sequence of percepts can influence the actions of an agent.
  • 7. Sensors & Effectors  It can change the environment through effectors.  An operation involving an actuator is called an action.  Actions can be grouped in to action sequences.  So an agent program implement mapping from percept sequences to actions.
  • 8. Agents  Autonomous Agent: Decide autonomously which action to take in the current situation to maximize progress towards its goals.  Performance measure: An objective criterion for success of an agent's behavior.  E.g., performance measure of a vacuum- cleaner agent could be amount of dirt cleaned up, amount of time taken, amount of electricity consumed, amount of noise generated, etc.
  • 9. Examples of agents  Humans eyes, ears, skin, taste buds, etc. for Sensors. hands, fingers, legs, mouth for effectors.  Robots camera, infrared, bumper, etc. for sensors. grippers, wheels, lights, speakers, etc. for effectors.
  • 10. Structure of agents  A simple agent program can be defined mathematically as an agent function which maps every possible precepts sequence to a possible action the agent can perform.  F: p*-> A  the term percept is use to the agent's perceptional inputs at any given instant.
  • 11. Intelligent agents  Fundamental faculties of intelligence Acting Sensing Understanding, Reasoning, learning  In order to act you must sense. Blind actions is not a characterization of intelligence.  Robotics: sensing and acting. Understanding not necessary.  Sensing needs understanding to be useful.
  • 12. Intelligent Agents  Intelligent Agent: must sense, must act, must be autonomous(to some extent) must be rational.
  • 13. Rational Agent  AI is about building rational agents.  An agent is something that perceives and acts.  A rational agent always does the right thing. What are the functionalities(goals)? What are the components? How do we build them?
  • 14. Rationality  Perfect Rationality: Assumes that the rational agent knows all and will take the action that maximize the utility. Human beings do not satisfy this definition of rationality.
  • 15. Agent Environment  Environments in which agents operate can be defined in different ways.  It is helpful to view the following definitions as referring to the way the environment appears from the point of view of the agent itself.
  • 16. Environment: Observability  Fully Observable: All of the environment relevant to the action being considered is observable. Such environments are convenient, since the agent is freed from the task of keeping track of changes in the environment.  Partially Observable: The relevant features of the environment are only partially observable.  Example: Fully obs: Chess; Partially obs: Poker
  • 17. Environment: Determinism  Deterministic: The next state of the environment is completely described by the current state and the agent’s action. e.g. Image Analysis  Stochastic: If an element of interference or uncertainty occurs then the environment is stochastic. A partially observable environment will appear to be stochastic to the agent. e.g. ludo  Strategic: Environment state wholly determined by the preceding state and the actions of multiple agents is called strategic. e.g. Chess
  • 18. Environment: Episodicity  Episodic/Sequential: An Episodic Environment means that subsequent episodes do not depend on what actions occurred in previous episodes. In a Sequential Environment, the agent engages in a series of connected episodes.
  • 19. Environment: Dynamism  Static Environment: does not change from one sate to next while the agent is considering its course of action. The only changes to the environment as those caused by the agent itself.  Dynamic Environment: Changes over time independent of the actions of the agent-and thus if an agent does not respond in a timely manner, this counts as a choice to do nothing.
  • 20. Environment: Continuity  Discrete/Continuous: If the number of distinct percepts and actions is limited, the environment is discrete, otherwise it is continuous.
  • 21. Classes of Intelligent Agents  Intelligent agents are grouped in to five classes based on their degree of perceived intelligence and capability.  Simple reflex agents  Model based reflex agents  Goal based agents  Utility based agents  Learning agents
  • 22. Simple reflex agents  Simple reflex agents act only on the basis of the current percept, ignoring the rest of the percept history. The agent function is based on the condition-action rule: if condition then action.  Succeeds when the environment is fully observable.  Some reflex agents can also contain information on their current state which allows them to disregard conditions.
  • 24. Model based reflex agents  A model-based agent can handle a partially observable environment.  Its current state is stored inside the agent maintaining some kind of structure which describes the part of the world which cannot be seen.  This knowledge about "how the world evolves" is called a model of the world, hence the name "model-based agent".
  • 26. Goal based agents  Goal-based agents further expand on the capabilities of the model-based agents, by using "goal" information.  Goal information describes situations that are desirable. This allows the agent a way to choose among multiple possibilities, selecting the one which reaches a goal state.  Search and planning are the subfields of artificial intelligence devoted to finding action sequences that achieve the agent's goals.
  • 28. Utility based agents  Goal-based agents only distinguish between goal states and non-goal states.  It is possible to define a measure of how desirable a particular state is. This measure can be obtained through the use of a utility function which maps a state to a measure of the utility of the state.  A more general performance measure should allow a comparison of different world states according to exactly how happy they would make the agent. The term utility, can be used to describe how "happy" the agent is.
  • 30. Learning agents  Learning has an advantage that it allows the agents to initially operate in unknown environments and to become more competent than its initial knowledge alone might allow.  The most important distinction is between the "learning element", which is responsible for making improvements, and the "performance element", which is responsible for selecting external actions.  The learning element uses feedback from the "critic" on how the agent is doing and determines how the performance element should be modified to do better in the future.
  • 31. Learning agents  The last component of the learning agent is the "problem generator". It is responsible for suggesting actions that will lead to new and informative experiences.
  • 33. Applications of Intelligent Agents  Intelligent agents are applied as automated online assistants, where they function to perceive the needs of customers in order to perform individualized customer service.  Use in smart phones in future.