0% found this document useful (0 votes)
7 views118 pages

AI - Unit 1

The document outlines an introductory course on Artificial Intelligence (AI) led by Dr. Padmapani P. Tribhuvan, covering the scope, outcomes, and foundational concepts of AI. Key topics include intelligent agents, problem-solving, natural language processing, and various definitions and philosophies of AI. The course also discusses assessment methods and historical milestones in AI development.

Uploaded by

jagdalesaee024
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
7 views118 pages

AI - Unit 1

The document outlines an introductory course on Artificial Intelligence (AI) led by Dr. Padmapani P. Tribhuvan, covering the scope, outcomes, and foundational concepts of AI. Key topics include intelligent agents, problem-solving, natural language processing, and various definitions and philosophies of AI. The course also discusses assessment methods and historical milestones in AI development.

Uploaded by

jagdalesaee024
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 118

Introduction to Course and AI

Course : Artificial Intelligence


Course Code : BTCOC701
Unit 1 : Introduction and Intelligent Agents
Lecture 1
Date: 07/08/2023

Dr. Padmapani P. Tribhuvan


Assistant Professor,
Department of Computer Science and Engineering
Deogiri Institute of Engineering and Management Studies,
Aurangabad.

Artificial Intelligence by Dr. Padmapani


1
Tribhuvan
Contents
• Introduction and Scope
• Course Outcomes
• Assessments
• What is AI?
• Definitions of AI
• The Foundations of Artificial Intelligence
Artificial Intelligence by Dr. Padmapani
2
Tribhuvan
Introduction and Scope of course
• A brief introduction to
– the philosophy of AI
– breadth of ideas in AI
• AI way of thinking

Artificial Intelligence by Dr. Padmapani


3
Tribhuvan
Introduction and Scope of course
• Theory
• Modeling
• Algorithms
• Applications

Artificial Intelligence by Dr. Padmapani


4
Tribhuvan
Introduction and Scope of course
• Theory
• Modeling
• Algorithms
• Applications

Artificial Intelligence by Dr. Padmapani


5
Tribhuvan
Teaching and Examination Scheme
University

Lectures Tutorials Practical MSE CA ESE


2 1 - 20 20 60

Institute
Lectures Tutorials Practical MSE CA ESE
2 1 2 20 20 60

Artificial Intelligence by Dr. Padmapani


6
Tribhuvan
Course Contents
• Introduction and Intelligent Agents
• Problem Solving, Constraint Satisfaction
Problems, Game Playing
• Knowledge & Reasoning
• Probabilistic Reasoning
• Natural Language processing

Artificial Intelligence by Dr. Padmapani


7
Tribhuvan
Resources
• Peter Norvig, Artificial Intelligence: A Modern Approach,
Third Edition.
• NPTEL : An Introduction to Artificial Intelligence, IIT Delhi
by Mausam. https://nptel.ac.in/courses/106102220
• Artificial Intelligence: Search Methods for Problem Solving,
IIT Madras, Prof. Deepak Khemani
• https://nptel.ac.in/courses/106106126

Artificial Intelligence by Dr. Padmapani


8
Tribhuvan
Course Outcomes
You will be able to
CO1 To describe the concepts of Artificial Intelligence, Intelligent Agents,
Logical Agents. (BTL2 : Understand)
CO2 To solve search problems, constraint satisfaction problems and
adversarial search algorithms problems. (BTL3 : Apply)
CO3 To carry out proofs in first order and propositional logic using
techniques such as resolution, nification, backward and forward chaining..
(BTL3 : Apply)
CO4 To describe representation knowledge in an uncertain domain. (BTL2
: Understand)
CO5 To describe use of Artificial Intelligence in Natural Language
Processing. .(BTL2 : Understand)
Artificial Intelligence by Dr. Padmapani
9
Tribhuvan
Assessments
1. Assignment 1 (10 Marks) - CO 1,2
2. MSE : 20 Marks - CO 1,2
3. Assignment 2 (10 Marks) - CO 3,4,5

NO Re-test or Assessment will be conducted.

Artificial Intelligence by Dr. Padmapani


10
Tribhuvan
Introduction
Course : Elective - V (B) Artificial Intelligence
Course Code : BTCOE603-B
Unit 1 : Introduction and Intelligent Agents
Lecture 2
Date: 09/08/2023

Dr. Padmapani P. Tribhuvan


Assistant Professor,
Department of Computer Science and Engineering
Deogiri Institute of Engineering and Management Studies,
Aurangabad.

Artificial Intelligence by Dr. Padmapani


11
Tribhuvan
Contents
• What is AI ?
• Definitions of AI
• The Foundations of Artificial Intelligence

Artificial Intelligence by Dr. Padmapani


12
Tribhuvan
Outcomes
• You will be able
– To describe different definitions of AI
– To describe the Foundations of Artificial
Intelligence

Artificial Intelligence by Dr. Padmapani


13
Tribhuvan
What is AI?

Artificial Intelligence by Dr. Padmapani


14
Tribhuvan
Science of AI

Artificial Intelligence by Dr. Padmapani


15
Tribhuvan
Science of AI

Artificial Intelligence by Dr. Padmapani


16
Tribhuvan
What is intelligence ?

Artificial Intelligence by Dr. Padmapani


17
Tribhuvan
What is intelligence ?
• Chess game
• 1950
• Year 1997: In the year 1997, IBM Deep Blue beats world chess
champion, Gary Kasparov, and became the first computer to
beat a world chess champion.
• Today

Artificial Intelligence by Dr. Padmapani


18
Tribhuvan
What is intelligence ?

Artificial Intelligence by Dr. Padmapani


19
Tribhuvan
What is AI?
• The field of artificial intelligence, or AI,
attempts to understand intelligent entities. (One
reason to study it is to learn more about
ourselves.)
• AI strives to build intelligent entities as well as
understand them.
Artificial Intelligence by Dr. Padmapani
20
Tribhuvan
Intelligence vs. Human

Artificial Intelligence by Dr. Padmapani


21
Tribhuvan
What is your own philosophy of life?

Artificial Intelligence by Dr. Padmapani


22
Tribhuvan
Definitions of AI

Artificial Intelligence by Dr. Padmapani


23
Tribhuvan
What is AI?

Artificial Intelligence by Dr. Padmapani


24
Tribhuvan
Artificial Intelligence by Dr. Padmapani
25
Tribhuvan
• Turing test approach

Artificial Intelligence by Dr. Padmapani


26
Tribhuvan
• Turing test approach

Artificial Intelligence by Dr. Padmapani


27
Tribhuvan
• Turing test approach

Artificial Intelligence by Dr. Padmapani


28
Tribhuvan
• Turing test approach

Artificial Intelligence by Dr. Padmapani


29
Tribhuvan
The computer would need to possess the
following capabilities :
1. Natural language processing to enable
it to communicate successfully in English
2. knowledge representation to store what
it knows or hear
3. automated reasoning to use the stored
information to answer questions and to
• Turing test approach draw new conclusions
4. machine learning to adapt to new
circumstances and to detect and extrapolate
patterns.
5. Computer Vision to perceive objects
6. robotics to manipulate objects and move
about.
Artificial Intelligence by Dr. Padmapani
30
Tribhuvan
The computer would need to possess the
following capabilities :
1. Natural language processing to enable
it to communicate successfully in English
2. knowledge representation to store what
it knows or hear
3. automated reasoning to use the stored
information to answer questions and to
• Turing test approach draw new conclusions
4. machine learning to adapt to new
• These six disciplines compose circumstances and to detect and extrapolate
most of AI patterns.
5. Computer Vision to perceive objects
6. robotics to manipulate objects and move
about.
Artificial Intelligence by Dr. Padmapani
31
Tribhuvan
• Cognitive modeling approach
• If we are going to say that a given program thinks like a human,
we must have some way of determining how humans think.
• We need to get inside the actual workings of human minds.
Artificial Intelligence by Dr. Padmapani
32
Tribhuvan
• Three ways
1. through introspection - trying to catch our own thoughts as they
go by
2. through psychological experiments—observing a person in
action
3. through brain imaging - observing the brain in action
Artificial Intelligence by Dr. Padmapani
33
Tribhuvan
GPS (General Problem
Solver )

• Cognitive modeling
approach

Artificial Intelligence by Dr. Padmapani


34
Tribhuvan
GPS (General Problem
Solver )

Artificial Intelligence by Dr. Padmapani


35
Tribhuvan
GPS (General Problem
Solver )

The interdisciplinary field of cognitive science brings together


computer models from AI and experimental techniques from
psychology to construct precise and testable theories of the human
mind.

Artificial Intelligence by Dr. Padmapani


36
Tribhuvan
• Aristotle was one of the first to attempt
to codify "thinking".
His syllogisms provided patterns of
argument structure that always gave
correct conclusions, giving correct
premises.
• Example: All computers use energy.
Using energy always generates heat.
Therefore, all computers generate heat.
The “laws of thought” • This initiate the field of logic. Formal
approach logic was developed in the late
nineteenth century. This was the first
step toward enabling computer programs
to reason logically.
Artificial Intelligence by Dr. Padmapani
37
Tribhuvan
• Acting rationally means acting so as to
achieve one's goals, given one's beliefs.
• An agent is just something that perceives
and acts.
• In the logical approach to AI, the emphasis
is on correct inferences.
The rational agent approach

Artificial Intelligence by Dr. Padmapani


38
Tribhuvan
Summary
1. Acting Humanly – Turing test approach
2. Thinking Humanly – cognitive modeling
approach
3. Thinking Rationally - The “laws of thought”
approach
4. Acting Rationally - The rational agent
approach
Artificial Intelligence by Dr. Padmapani
39
Tribhuvan
The Foundations of Artificial Intelligence
1. Philosophy
2. Mathematics
3. Economics
4. Neuroscience
5. Computer engineering
6. Control theory and cybernetics
7. Linguistics
Artificial Intelligence by Dr. Padmapani
40
Tribhuvan
The Foundations of Artificial Intelligence
1. Philosophy
• Can formal rules be used to draw valid
conclusions?
• How does the mind arise from a physical brain?
• Where does knowledge come from?
• How does knowledge lead to action?
Artificial Intelligence by Dr. Padmapani
41
Tribhuvan
The Foundations of Artificial Intelligence
2. Mathematics
• What are the formal rules to draw valid
conclusions?
• What can be computed?
• How do we reason with uncertain
information?
Artificial Intelligence by Dr. Padmapani
42
Tribhuvan
The Foundations of Artificial Intelligence
3. Economics
• How should we make decisions so as to
maximize payoff?
• How should we do this when others may not
go along?
• How should we do this when the payoff may
be far in the future?
Artificial Intelligence by Dr. Padmapani
43
Tribhuvan
The Foundations of Artificial Intelligence
4. Neuroscience
• How do brains process information?

Artificial Intelligence by Dr. Padmapani


44
Tribhuvan
The Foundations of Artificial Intelligence
5. Computer engineering
• How can we build an efficient computer?

Artificial Intelligence by Dr. Padmapani


45
Tribhuvan
The Foundations of Artificial Intelligence
6. Control theory and cybernetics
• How can artifacts operate under their own
control?

Artificial Intelligence by Dr. Padmapani


46
Tribhuvan
The Foundations of Artificial Intelligence
7. Linguistics
• How does language relate to thought?

Artificial Intelligence by Dr. Padmapani


47
Tribhuvan
The Foundations of Artificial Intelligence
1. Philosophy
2. Mathematics
3. Economics
4. Neuroscience
5. Computer engineering
6. Control theory and cybernetics
7. Linguistics
Artificial Intelligence by Dr. Padmapani
48
Tribhuvan
History of AI
• Task : Watch following video and note down
important event and years.

• https://youtu.be/yaL5ZMvRRqE

Artificial Intelligence by Dr. Padmapani


49
Tribhuvan
History
• Maturation of Artificial Intelligence (1943-1952)
1. Year 1943: The first work which is now recognized as AI was done by Warren
McCulloch and Walter pits in 1943. They proposed a model of artificial neurons.
2. Year 1949: Donald Hebb demonstrated an updating rule for modifying the
connection strength between neurons. His rule is now called Hebbian learning.
3. Year 1950: The Alan Turing who was an English mathematician and pioneered
Machine learning in 1950. Alan Turing publishes "Computing Machinery and
Intelligence" in which he proposed a test. The test can check the machine's ability to
exhibit intelligent behavior equivalent to human intelligence, called a Turing test.

Artificial Intelligence by Dr. Padmapani


50
Tribhuvan
History
• The birth of Artificial Intelligence (1952-1956)
1. Year 1955: An Allen Newell and Herbert A. Simon created the "first artificial
intelligence program "Which was named as "Logic Theorist". This program had
proved 38 of 52 Mathematics theorems, and find new and more elegant proofs for
some theorems.
2. Year 1956: The word "Artificial Intelligence" first adopted by American Computer
scientist John McCarthy at the Dartmouth Conference. For the first time, AI coined
as an academic field.
3. At that time high-level computer languages such as FORTRAN, LISP, or COBOL
were invented. And the enthusiasm for AI was very high at that time.

Artificial Intelligence by Dr. Padmapani


51
Tribhuvan
History
• The golden years-Early enthusiasm (1956-1974)
• Year 1966: The researchers emphasized developing
algorithms which can solve mathematical problems.
Joseph Weizenbaum created the first chatbot in 1966,
which was named as ELIZA.
• Year 1972: The first intelligent humanoid robot was
built in Japan which was named as WABOT-1.

Artificial Intelligence by Dr. Padmapani


52
Tribhuvan
History
• The first AI winter (1974-1980)
• The duration between years 1974 to 1980 was the
first AI winter duration. AI winter refers to the
time period where computer scientist dealt with a
severe shortage of funding from government for AI
researches.
• During AI winters, an interest of publicity on
artificial intelligence was decreased.
Artificial Intelligence by Dr. Padmapani
53
Tribhuvan
History
• A boom of AI (1980-1987)
• Year 1980: After AI winter duration, AI came back with
"Expert System". Expert systems were programmed that
emulate the decision-making ability of a human expert.
• In the Year 1980, the first national conference of the
American Association of Artificial Intelligence was held at
Stanford University.

Artificial Intelligence by Dr. Padmapani


54
Tribhuvan
History
• The second AI winter (1987-1993)
• The duration between the years 1987 to 1993 was the second
AI Winter duration.
• Again Investors and government stopped in funding for AI
research as due to high cost but not efficient result. The
expert system such as XCON was very cost effective.

Artificial Intelligence by Dr. Padmapani


55
Tribhuvan
History
• The emergence of intelligent agents (1993-2011)
• Year 1997: In the year 1997, IBM Deep Blue beats world chess
champion, Gary Kasparov, and became the first computer to beat a
world chess champion.
• Year 2002: for the first time, AI entered the home in the form of
Roomba, a vacuum cleaner.
• Year 2006: AI came in the Business world till the year 2006.
Companies like Facebook, Twitter, and Netflix also started using
AI.

Artificial Intelligence by Dr. Padmapani


56
Tribhuvan
History
• Deep learning, big data and artificial general intelligence (2011-present)
• Year 2011: In the year 2011, IBM's Watson won jeopardy, a quiz show, where it had to solve the
complex questions as well as riddles. Watson had proved that it could understand natural language
and can solve tricky questions quickly.
• Year 2012: Google has launched an Android app feature "Google now", which was able to provide
information to the user as a prediction.
• Year 2014: In the year 2014, Chatbot "Eugene Goostman" won a competition in the infamous
"Turing test."
• Year 2018: The "Project Debater" from IBM debated on complex topics with two master debaters
and also performed extremely well.
• Google has demonstrated an AI program "Duplex" which was a virtual assistant and which had
taken hairdresser appointment on call, and lady on other side didn't notice that she was talking with
the machine.

Artificial Intelligence by Dr. Padmapani


57
Tribhuvan
History

Artificial Intelligence by Dr. Padmapani


58
Tribhuvan
The State of the Art
1. Robotics vehicle
2. Speech Recognition
3. Autonomous planning and scheduling
4. Game playing
5. Spam fighting
6. Logistics planning
7. Robotics
8. Machine Translation
Artificial Intelligence by Dr. Padmapani
59
Tribhuvan
Thank You !!!

Artificial Intelligence by Dr. Padmapani


60
Tribhuvan
Intelligent Agents
Course : Elective - V (B) Artificial Intelligence
Course Code : BTCOE603-B
Unit 1 : Introduction and Intelligent Agents
Lecture 4
Date: 14/08/2023

Dr. Padmapani P. Tribhuvan


Assistant Professor,
Department of Computer Science and Engineering
Deogiri Institute of Engineering and Management Studies,
Aurangabad.

Artificial Intelligence by Dr. Padmapani


61
Tribhuvan
Contents
• Agents
• The Nature of Environment
• The Structure of Agents

Artificial Intelligence by Dr. Padmapani


62
Tribhuvan
Summary
1. Acting Humanly – Turing test approach
2. Thinking Humanly – cognitive modeling
approach
3. Thinking Rationally - The “laws of thought”
approach
4. Acting Rationally - The rational agent
approach
Artificial Intelligence by Dr. Padmapani
63
Tribhuvan
Agent
• An agent is anything that can be viewed as perceiving its
environment through sensors and acting upon that
environment through actuators.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Percept and Percept Sequence
• Percept refers to the agent’s perceptual inputs at any
given instant.
• An agent’s percept sequence is the complete history of
everything the agent has ever perceived.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Agent Function and Agent Program
• An agent’s behavior is described by the agent function
that maps any given percept sequence to an action.
• The agent function for an artificial agent will be
implemented by an agent program.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Good Behavior : The concept of Rationality

• A rational agent is one that does the right


thing.
• Performance Measure - An objective criterion
for success of agent’s behaviour.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Rationality
• What is rational at any given time depends on four
things:
1. The performance measure that defines the
criterion of success.
2. The agent’s prior knowledge of the environment.
3. The actions that the agent can perform.
4. The agent’s percept sequence to date.
Artificial Intelligence by Dr. Padmapani
Tribhuvan
Definition of a Rational Agent
• For each possible percept sequence, a rational
agent should select an action that is expected to
maximize its performance measure, given the
evidence provided by the percept sequence and
whatever built-in knowledge the agent has.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Example

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Example

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Example

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Example

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Example

Artificial Intelligence by Dr. Padmapani


Tribhuvan
The Nature of Environment

• We must think about task environments, which


are essentially the “problems” to which
rational agents are the “solutions.
1. Specifying the Task Environments
2. Properties of Task Environments

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Specifying the Task Environments
• In designing an agent, the first step must always
be to specify the task environment as fully as
possible.
• PEAS (Performance, Environment, Actuators,
Sensors) Description

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Specifying the Task Environments

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Activity
• For any THREE of the following activities, give a PEAS
description of the task environment.
1. Medical Diagnosis System
2. Satellite Image Analysis System
3. Part-picking Robot
4. Refinery Controller
5. Interactive English Tutor

Artificial Intelligence by Dr. Padmapani


Tribhuvan
The Nature of Environment

• We must think about task environments, which


are essentially the “problems” to which
rational agents are the “solutions”.
1. Specifying the Task Environments
2. Properties of Task Environments

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Specifying the Task Environments

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Specifying the Task Environments - Activity
• For any THREE of the following activities, give a PEAS
description of the task environment.
1. Medical Diagnosis System
2. Satellite Image Analysis System
3. Part-picking Robot
4. Refinery Controller
5. Interactive English Tutor

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Activity Solution

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Artificial Intelligence by Dr. Padmapani
Tribhuvan
Properties of Task Environments
• Fully observable vs. partially observable:
• If an agent’s sensors give it access to the complete
state of the environment at each point in time,
then we say that the task environment is fully
observable.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Properties of Task Environments
• Single agent vs. multiagent
– Competitive multiagent environment
– Cooperative multiagent environment

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Properties of Task Environments
• Deterministic vs. stochastic.
• If the next state of the environment is completely
determined by the current state and the action
executed by the agent, then we say the
environment is deterministic; otherwise, it is
stochastic.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Properties of Task Environments
• Episodic vs. sequential
• In an episodic task environment, the agent’s
experience is divided into atomic episodes. In
each episode the agent receives a percept and then
performs a single action.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Properties of Task Environments
• Static vs. dynamic
• If the environment can change while an agent is
deliberating, then we say the environment is
dynamic for that agent; otherwise, it is static.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Properties of Task Environments
• Discrete vs. continuous:
• The discrete/continuous distinction applies to the
state of the environment, to the way time is
handled, and to the percepts and actions of the
agent.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Properties of Task Environments
• Known vs. unknown
• In a known environment, the outcomes for all
actions are given.
• If the environment is unknown, the agent will
have to learn how it works in order to make good
decisions.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Examples Task Environments

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Thank You !!!

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Intelligent Agents
Course : Elective - V (B) Artificial Intelligence
Course Code : BTCOE603-B
Unit 1 : Introduction and Intelligent Agents
Lecture 5
Date: 24/03/2022

Dr. Padmapani P. Tribhuvan


Assistant Professor,
Department of Computer Science and Engineering
Deogiri Institute of Engineering and Management Studies,
Aurangabad.

Artificial Intelligence by Dr. Padmapani


93
Tribhuvan
Contents
• Types of Agent Program
• How the components of agent programs work?
• Summary of Intelligent Agents

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Types of Agent programs
• Simple reflex agents
• Model-based reflex agents
• Goal-based agents and
• Utility-based agents.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Simple Reflex Agents
• The simplest kind of agent is the simple reflex agent. These
agents select actions on the basis of the current percept,
ignoring the rest of the percept history.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Simple Reflex Agents

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Simple Reflex Agents

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Model-based Reflex Agents
• Knowledge about “how the world works” is called a model of the
world.
• An agent that uses such a model is called a model-based agent.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Model-based Reflex Agents

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Model-based Reflex Agents

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Goal based Agents
• The agent needs some sort of goal information that describes situations
that are desirable.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Goal based Agents

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Utility based Agents
• A more general performance measure should allow a comparison of different
world states according to exactly how happy they would make the agent.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Utility based Agents

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Learning Agents
• A learning agent can be divided into four conceptual components,
1. Learning Element (responsible for making improvements)
2. Performance Element (responsible for selecting external actions)
3. Critic (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. )
4. Problem Generator (responsible for suggesting actions that will lead to new
and informative experiences. )

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Learning Agents

Artificial Intelligence by Dr. Padmapani


Tribhuvan
How the components of agent programs work?

1. Atomic Representation
2. Factored Representations
3. Structured Representation

Artificial Intelligence by Dr. Padmapani


Tribhuvan
How the components of agent programs work?

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Type State representation Focus
Atomic States are indivisible; No Search on atomic states;
internal structure
Propositional (Factored) States are made of state Search+inference in logical
variables that take values (prop logic) and
(Propositional or probabilistic (bayes nets)
Multi-valued or Continuous) representations

Relational (Structured) States describe the objects Search+Inference in


in the world and their inter- predicate logic (or relational
relations prob. Models)

First-order (Structured) +functions over objects Search+Inference in first


order logic (or first order
Artificial Intelligence by Dr. Padmapani
probabilistic models)
Tribhuvan
Artificial Intelligence by Dr. Padmapani
Tribhuvan
Type State representation Focus
Atomic States are indivisible; No Search on atomic states;
internal structure
Propositional (Factored) States are made of state Search+inference in logical
variables that take values (prop logic) and
(Propositional or probabilistic (bayes nets)
Multi-valued or Continuous) representations

Relational (Structured) States describe the objects Search+Inference in


in the world and their inter- predicate logic (or relational
relations prob. Models)

First-order (Structured) +functions over objects Search+Inference in first


order logic (or first order
Artificial Intelligence by Dr. Padmapani
probabilistic models)
Tribhuvan
Artificial Intelligence by Dr. Padmapani
Tribhuvan
Type State representation Focus
Atomic States are indivisible; No Search on atomic states;
internal structure
Propositional (Factored) States are made of state Search+inference in logical
variables that take values (prop logic) and
(Propositional or probabilistic (bayes nets)
Multi-valued or Continuous) representations

Relational (Structured) States describe the objects Search+Inference in


in the world and their inter- predicate logic (or relational
relations prob. Models)

First-order (Structured) +functions over objects Search+Inference in first


order logic (or first order
Artificial Intelligence by Dr. Padmapani
probabilistic models)
Tribhuvan
Artificial Intelligence by Dr. Padmapani
Tribhuvan
Summary
• An agent is something that perceives and acts in an environment. The agent function for an
agent specifies the action taken by the agent in response to any percept sequence.
• The performance measure evaluates the behaviour of the agent in an environment. A
rational agent acts so as to maximize the expected value of the performance measure, given
the percept sequence it has seen so far.
• A task environment specification includes the performance measure, the external
environment, the actuators, and the sensors. In designing an agent, the first step must always
be to specify the task environment as fully as possible.
• Task environments vary along several significant dimensions. They can be fully or partially
observable, single-agent or multiagent, deterministic or stochastic, episodic or sequential,
static or dynamic, discrete or continuous, and known or unknown.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Summary
• The agent program implements the agent function. There exists a variety of basic
agent-program designs reflecting the kind of information made explicit and used in the
decision process. The designs vary in efficiency, compactness, and flexibility. The
appropriate design of the agent program depends on the nature of the environment.
• Simple reflex agents respond directly to percepts, whereas model-based reflex agents
maintain internal state to track aspects of the world that are not evident in the current
percept. Goal-based agents act to achieve their goals, and utility-based agents try to
maximize their own expected “happiness.”
• All agents can improve their performance through learning.

Artificial Intelligence by Dr. Padmapani


Tribhuvan
Thank You !!!

Artificial Intelligence by Dr. Padmapani


Tribhuvan

You might also like