Artificial Intelligence: A Brief Overview

Dr. A. Vijayalakshmi
School of Computer Science and Engineering
VIT Chennai
 MODULE-I
Introduction, Overview of Artificial intelligence
• Introduction
• Evolution of AI
• State of Art
• Different Types of Artificial Intelligence
• Applications of AI
• Subfields of AI
• Intelligent Agents
• Structure of Intelligent Agents
• Environments
 AI - Definition

Intelligence Artificial Artificial Intelligence

• Branch of computer Science

• Imitate the roles of human brain
 Introduction to AI
What is Intelligence?

Intelligence, taken as a whole, consists of

the following skills:- the capacity to learn and
solve problems
1. the ability to acquire and perceive
2. the ability to understand and apply
knowledge
3. the ability to act and communicate ideas
 An Intelligent Entity
INTERNAL
INPUTS
PROCESSES
Has knowledge
Senses environment Has understanding

See
Hear Can Reason
Touch
Taste
Smell

Exhibits behaviour

OUTPUTS
 Real and Artificial Intelligence
• Human
– Possess real intelligence

• Machine
– Possess artificial intelligence
 Brain vs. Computer
• In AI, we compare the brain (or the mind) and the
computer
– Our hope: the brain is a form of computer
– Our goal: we can create computer intelligence through
programming just as people become intelligent by learning

But we see that the computer

is not like the brain

The computer performs tasks

without understanding what
its doing

Does the brain understand

what its doing when it solves
problems?
 What is AI?
How does Howd ow e
the human em ulateth e
brain work? huma nb rain?

How dowe
c reate
What is in
tellig
ence?
intelligence?
 Why AI?
• Two main goals of AI:
– To understand human intelligence better.
– To create useful “smart” programs
Definition of AI
 General Definitions of AI
• Artificial intelligence
– It is a branch of computer science which deals
with the study and creation of computer
systems that exhibit some form of intelligence.
– Building intelligent systems
– It is the study and design of intelligent agents
 AI Definitions
• The study of how to make programs/computers do
things that people do better
• The study of how to make computers solve problems Thinking
which require knowledge and intelligence machines or
• The exciting new effort to make computers think … machine
machines with minds intelligence
• The automation of activities that we associate with
human thinking (e.g., decision-making, learning…)
• The art of creating machines that perform functions
that require intelligence when performed by people Studying
• The study of mental faculties through the use of cognitive
computational models
• A field of study that seeks to explain and emulate
intelligent behavior in terms of computational Problem
processes Solving and
• The branch of computer science that is concerned CS
with the automation of intelligent behavior
Traditional Vs ML Algorithms
Relation with other Disciplines
 Disciplines of AI
• AI as a field of study
– Philosophy
– Mathematics
– Economics
– Neuroscience
– Psychology
– Computer engineering
– Control theory and cybernetics Linguistics
– AI is part science, part engineering
• AI often must study other domains in order to implement
systems
– e.g., medicine and medical practices for a medical diagnostic system,
engineering and chemistry to monitor a chemical processing plant
 AI prehistory
 Philosophy Logic, methods of reasoning, mind as
physical system foundations of learning,
language, rationality
 Mathematics Formal representation and proof
algorithms, computation, (un)decidability,
(in)tractability, probability
 Economics utility, decision theory
 Neuroscience physical substrate for mental activity
 Psychology phenomena of perception and motor
control, experimental techniques
 Computer building fast computers engineering
 Control theory design systems that maximize an objective
function over time
 Linguistics knowledge representation, grammar
History (Evolution) of AI
 A bridged history of AI
 1943 McCulloch & Pitts: Boolean circuit model of brain
 1950 Turing's "Computing Machinery and Intelligence"
 1956 Dartmouth meeting: "Artificial Intelligence" adopted
 1952—69 Look, Ma, no hands!
 1950s Early AI programs, including Samuel's checkers
program, Newell & Simon's Logic Theorist,
Gelernter's Geometry Engine
 1965 Robinson's complete algorithm for logical reasoning
 1966—73 AI discovers computational complexity
Neural network research almost disappears
 1969—79 Early development of knowledge-based systems
 1980-- AI becomes an industry
 1986-- Neural networks return to popularity
 1987-- AI becomes a science
 1995-- The emergence of intelligent agents
 A Brief History of AI: 1950s
• Computers were thought of as an electronic brains
• Term “Artificial Intelligence” coined by John McCarthy
– John McCarthy also created Lisp in the late 1950s
• Alan Turing defines intelligence as passing the Imitation
Game (Turing Test)
• AI research largely revolves around toy domains
– Computers of the era didn’t have enough power or memory to
solve useful problems
– Problems being researched include
• games (e.g., checkers)
• primitive machine translation
• blocks world (planning and natural language understanding within the
toy domain)
• early neural networks researched: the perceptron
• automated theorem proving and mathematics problem solving
 The 1960s
• AI attempts to move beyond toy domains
• Syntactic knowledge alone does not work, domain
knowledge required
– Early machine translation could translate English to Russian
(“the spirit is willing but the flesh is weak” becomes “the
vodka is good but the meat is spoiled”)
• Earliest expert system created: Dendral
• Perceptron research comes to a grinding halt when it is
proved that a perceptron cannot learn the XOR
operator
• US sponsored research into AI targets specific areas –
not including machine translation
• Weizenbaum creates Eliza to demonstrate the futility of
AI
 1970s
• AI researchers address real-world problems and solutions through
expert (knowledge-based) systems
– Medical diagnosis
– Speech recognition
– Planning
– Design
• Uncertainty handling implemented
– Fuzzy logic
– Certainty factors
– Bayesian probabilities
• AI begins to get noticed due to these successes
– AI research increased
– AI labs sprouting up everywhere
– AI shells (tools) created
– AI machines available for Lisp programming
• Criticism: AI systems are too brittle, AI systems take too much time
and effort to create, AI systems do not learn
 1980s: AI Winter
• Funding dries up leading to the AI Winter
– Too many expectations were not met
– Expert systems took too long to develop, too much money to
invest, the results did not pay off
• Neural Networks to the rescue!
– Expert systems took programming, and took dozens of man-
years of efforts to develop, but if we could get the computer
to learn how to solve the problem…
– Multi-layered back-propagation networks got around the
problems of perceptrons
– Neural network research heavily funded because it promised
to solve the problems that symbolic AI could not
• By 1990, funding for neural network research was
slowly disappearing as well
– Neural networks had their own problems and largely could
not solve a majority of the AI problems being investigated
– Panic! How can AI continue without funding?
 1990s: ALife
• The dumbest smart thing you can do is staying alive
– We start over – lets not create intelligence, lets just create
“life” and slowly build towards intelligence
• Alife is the lower bound of AI
– Alife includes
• evolutionary learning techniques (genetic algorithms)
• artificial neural networks for additional forms of learning
• perception and motor control
• adaptive systems
• modeling the environment
• Let’s disguise AI as something new, maybe we’ll get
some funding that way!
– Problems: genetic algorithms are useful in solving some
optimization problems and some search-based problems, but
not very useful for expert problems
– perceptual problems are among the most difficult being
solved, very slow progress
 Today: The New (Old) AI
• Look around, who is doing AI research?
• By their own admission, AI researchers are not doing “AI”, they
are doing
– Intelligent agents, multi-agent systems/collaboration
– Ontologies
– Machine learning and data mining
– Adaptive and perceptual systems
– Robotics, path planning
– Search engines, filtering, recommendation systems
• Areas of current research interest:
– NLU/Information Retrieval, Speech Recognition
– Planning/Design, Diagnosis/Interpretation
– Sensor Interpretation, Perception, Visual Understanding
– Robotics
• Approaches
– Knowledge-based
– Ontologies
– Probabilistic (HMM, Bayesian Nets)
– Neural Networks, Fuzzy Logic, Genetic Algorithms
AI - History
 Sub-areas of AI
• Machine Learning
• Neural Network
• Natural Language Processing
• Deep Learning
• Cognitive Computing
• Computer Vision
 An Example
Computers making decisions in real-world
problems

apply

formulate solve
Artificial Intelligence

Machine
Learning

Deep
Learning
Types of Artificial Intelligence
• Weak AI: also known as narrow AI, is designed
and trained to complete a specific task.
• Ex: Industrial robots and virtual personal
assistants, such as Apple's Siri.
• Weak AI, focuses on one narrow task and
cannot perform beyond its limitations.
• It targets a single subset of cognitive abilities
and advances in that spectrum.
• IBM Watson supercomputer is another
example of a Narrow AI.
• It applies cognitive computing, machine
learning, and natural language processing to
process information and answers your
queries.
• Other examples of Narrow AI include google
translate, image recognition software,
recommendation systems, spam filtering, and
Google’s page-ranking algorithm.
• Strong AI: also known as artificial general
intelligence (AGI), describes programming that can
replicate the cognitive abilities of the human brain.
• When presented with an unfamiliar task, a strong
AI system can use fuzzy logic to apply knowledge
from one domain to another and find a solution
autonomously.
• A strong AI program should be able to pass both a
Turing test and the Chinese Room argument.
• Super AI : Super AI surpasses human intelligence and
can perform any task better than a human.
• The concept of artificial super intelligence sees AI
evolved to be so akin to human sentiments and
experiences.
• It doesn't merely understand them; it also evokes
emotions, needs, beliefs, and desires of its own.
• Its existence is still hypothetical. Some of the critical
characteristics of super AI include thinking, solving
puzzles, making judgments, and decisions on its own.
Applications of AI
 AI Applications
• Autonomous Planning
& Scheduling:
– Autonomous
rovers.
 AI Applications
• Autonomous Planning & Scheduling:
– Telescope scheduling
 AI Applications
• Autonomous Planning & Scheduling:
– Analysis of data:
 AI Applications
• Medicine:
– Image guided surgery
 AI Applications
• Medicine:
– Image analysis and enhancement
• Medicine:
– Personalized Treatment:
 AI Applications
• Transportatio
n:
– Autonomous
vehicle
control:
 AI Applications
• Transportation:
– Pedestrian detection:
 AI Applications
Games:
 AI Applications
• Games:
 AI Applications
• Robotic toys:
 Search engines
Science

Medicine/
Diagnosis

Labor
Appliances What else?
Artificial Intelligence
 Honda Humanoid Robot

Walk

Turn

[Link] Stairs
 Sony AIBO

[Link]
 Natural Language Question Answering

[Link] [Link]
Robot Teams

USC robotics Lab

 STATE OF THE ART
Robotic vehicles

• A driverless robotic car named STANLEY sped through the

rough terrain of the Mojave desert at 22 mph, finishing the
132-mile course first to win the 2005 DARPA Grand Challenge
 2004: Barstow, CA, to Primm, NV

150
150mile
mileoff-road
off-roadrobot
robotrace
race
across
acrossthe
theMojave
Mojavedesert
desert
Natural
Naturaland
andmanmade
manmadehazards
hazards
No
Nodriver,
driver,no
noremote
remotecontrol
control
No
Nodynamic
dynamicpassing
passing
Fastest
Fastestvehicle
vehiclewins
winsthe
therace
race
(and 2 million dollar prize)
(and 2 million dollar prize)
 ROBOTIC VEHICLES
Stanley Robot
Stanford Racing Team [Link]

• Robotic vehicles: A driverless robotic car named STANLEY sped

through the rough terrain of the Mojave dessert at 22 mph, finishing
the 132-mile course first to win the 2005 DARPA Grand Challenge
SENSOR INTERFACE PERCEPTION PLANNING&CONTROL USER INTERFACE

RDDF database corridor

Top level control Touch screen UI

pause/disable command
Wireless E-Stop
Laser 1 interface
RDDF corridor (smoothed and original) driving mode
Laser 2 interface

Laser 3 interface road center

Road finder Path planner
Laser 4 interface laser map

map trajectory
Laser 5 interface Laser mapper VEHICLE
Camera interface Vision mapper
vision map INTERFACE
obstacle list Steering control
Radar interface Radar mapper
vehicle state (pose, velocity) Touareg interface
vehicle
state Throttle/brake control
GPS position UKF Pose estimation
Power server interface
vehicle state (pose, velocity)
GPS compass

IMU interface Surface assessment

velocity limit

Wheel velocity

Brake/steering
heart beats Linux processes start/stop emergency stop

health status
Process controller Health monitor
power on/off
data

GLOBAL
Data logger File system
SERVICES
Communication requests Communication channels clocks

Inter-process communication (IPC) server Time server

Planning = Rolling out Trajectories
 Speech recognition

• A traveler calling United Airlines to book a flight can

have the en-tire conversation guided by an automated
speech recognition and dialog management system.
Autonomous planning and scheduling:
 Game playing
IBM's DEEP BLUE became the first computer program to defeat the
world champion in a chess match when it bested Garry Kasparov by a score of 3.5 to
2.5 in an exhibition match
Spam fighting

Logistics planning
 Robotics
• Roomba robotic vacuum cleaners
• PackBot
 Applications - AI
AI have placed its foot in all the fields
• Engineering Science
• Health Care
• Banking Sector
• Metrology
• Education
• Business
• Hospitality Industry
• Behavioral Sciences
• Tourism
• Legal Law
• Agriculture
• Fashion Technology
 Applications AI systems
• Robots
• Chess-playing program
• Voice recognition system
• Speech recognition system
• Grammar checker
• Pattern recognition
• Medial diagnosis
• Game Playing
• Machine Translation
• Resource Scheduling
• Expert systems (diagnosis, advisory, planning, etc)
• Machine learning
 AI – Trans-disciplinary Engineering
•No more Computer science, electrical,
Mechanical, civil engineers.
• Humanoid robots - Sophia
• Smart Home Automation (Appliances)
• Automatic cars/ Driverless cars
• Smart Green Houses
• 3-D Houses
• Flight Simulations
Current trends of AI
• AI for Cybersecurity
• AI for Communications
• Automated Business Processes
• Ethical AI
• Personalization
• The No-Code Revolution
• Prioritizing Diversity in AI
• AI in the Metaverse
• AI for Healthcare
• AI & IoT
• AI for Cyber security
– Cybercrime
– Cybe rsecurity and surveillance.
• security measures
– Face and voice recognition
– Video analysis
– Biometric authentication
• AI for Communications
– To generate visual, auditory, and text-based data
automatically
– AI chatbots
– to automate business customer interactions
• Chatbots can easily replace humans to
– Answer simple client questions
– Organize appointments
– Send out reminders or personalized offers
• Automated Business Processes
– Solve common business challenges
– Reduce pressure on employees
– Eliminate manual error
– Increase productivity and efficiency
• Ethical AI
– To monitor the quality and use of big data
– AI data compliance
– Platforms like Hadoop help organizations manage
big data applications.
• Personalization
– To help solve pressing global issues and make real
societal change
– Individualized education
– Safer and more efficient care in healthcare settings
for individuals
• Finance
– Fraud Detection
– Algorithmic Trading
– Personal Finance Management
• Climate and Environment
– Climate Modeling
– Wildlife Conservation
– Energy Optimization
• Education
– Personalized Learning
– Content Generation
– Language Learning
• Entertainment
– Content Creation
– Gaming
– Streaming Recommendations
• Transportation and Logistics
– Autonomous Vehicles
– Route Optimization
– Predictive Maintenance
• Customer Service
– AI Chatbots
– Sentiment Analysis
• Art and Design
– Generative Art
– Interior Design
• Agriculture
– Precision Farming
– Livestock Management
• Space Exploration
– Mission Planning
– Exoplanet Discovery
 Metaverse

• [Link]
v=rtLTZUaMSDQ&t=14s
4 Categories of AI
 4 Categories of Definition for AI
• Systems that act like humans
• Systems that think like humans
• Systems that think rationally
• Systems that act rationally

Systems that think Systems that think

like humans rationally

Systems that act Systems that act

like humans rationally
 1. Acting Humanly
• Also called Turing Test Approach
• The art of creating machines that perform
functions that require intelligence when
performed by people
– i.e., making computers to act like humans.

– Example : Turing Test

 Turing Test Approach
• This test dictates that a computer can pass if a
human interrogator is unable to differentiate
between written responses from a human and a
computer, after receiving written questions. H
• The Turing Test is a method of inquiry in artificial
intelligence (AI) for determining whether or not a
computer is capable of thinking like a human being.
The test is named after Alan Turing, the founder of
the Turing Test
 The Turing Test Approach

• Woman, Machine & Judge.

• Pass the test ?
• if the interrogator cannot tell
• if there is a computer or
Which one’s the computer?
• a human at the other end.
A
B
Qualities required to pass Turing Test
– The system requires these abilities to pass the test

– Natural language processing

• for communication with human
– Knowledge representation
• to store information effectively & efficiently
– Automated reasoning
• to retrieve & answer questions using the stored
information
– Machine learning
• to adapt to new circumstances
 Total Turing Test
• Can test subject’s perceptual abilities
• To pass the total Turing Test, the computer will
need
• Computer Vision to perceive objects
• Robotics to manipulate objects and move about
 2. Thinking Humanly

• Making computers to think like humans

• Goal is to build systems that function
internally in some way similar to human mind
• Also called cognitive modeling approach
 Cognitive Modeling Approach
– If we are going to say that a
• given program thinks like a human,
• Give a way of determining how humans thinks;
– We need to get inside the actual workings of human minds.
– Precise theory of the mind =>becomes possible to express the theory
as a computer program.

– Example GPS(General Problem Solver)

• comparing the reasoning steps of the program and human solving the same
problems.
 Cognitive Science
• Combines computer models of AI and
experimental techniques of psychology.
– Try to construct precise and testable theories of working of human
mind.

• cognitive science
– Is an interdisciplinary science
– draws on many fields (as psychology, artificial intelligence, linguistics,
and philosophy) in developing theories about human perception,
thinking, and learning
 3. Thinking Rationally
• Also called Laws of Thought approach
• Thinking “Right Thing”
• Making computers to think the “Right Thing”
• Relies on logic(to make inferences) rather than human to
measure correctness.
• Logic: provide a precise notation for statements about all
kinds of things in the world and the relations between
them.
• Syllogism: Provide patterns for argument structures
– Always give correct conclusion given correct premises.
– For example,
– Premise: John is a human and all humans are mortal
– Conclusion: John is mortal
– Can be done using logics. Example Propositional and predicate logic.
 Two obstacles: Laws of Thought of
Approach
• It’s not easy to take informal knowledge and
state it in the formal terms required by logical
notation, particularly when the knowledge is less
than 100% certain.
• Being able to solve a problem “in principle” and
doing so “in practice” are very different.
– i.e., 1. Informal Knowledge is not precise.
2. Difficult to model uncertainty
3. Theory and practice cannot be put together.
 4. Acting Rationally
• Also called Rational Agent Approach.
• Doing “Right Thing”
• Rational Agent – acts to achieve the best
outcome.
• An agent acts rationally if it selects the
action that maximizes it performance
measure.
 Applications - AI
AI have placed its foot in all the fields
• Engineering Science
• Health Care
• Banking Sector
• Metrology
• Education
• Business
• Hospitality Industry
• Behavioral Sciences
• Tourism
• Legal Law
• Agriculture
• Fashion Technology
 Applications AI systems
• Robots
• Chess-playing program
• Voice recognition system
• Speech recognition system
• Grammar checker
• Pattern recognition
• Medial diagnosis
• Game Playing
• Machine Translation
• Resource Scheduling
• Expert systems (diagnosis, advisory, planning, etc)
• Machine learning
 AI – Trans-disciplinary Engineering
•No more Computer science, electrical,
Mechanical, civil engineers.
• Humanoid robots - Sophia
• Smart Home Automation (Appliances)
• Automatic cars/ Driverless cars
• Smart Green Houses
• 3-D Houses
• Flight Simulations
Current trends of AI
• AI for Cybersecurity
• AI for Communications
• Automated Business Processes
• Ethical AI
• Personalization
• The No-Code Revolution
• Prioritizing Diversity in AI
• AI in the Metaverse
• AI for Healthcare
• AI & IoT
 Agents
• An agent is anything that can be viewed as
perceiving its environment through sensors and
acting upon that environment through actuators.
• Human agent: eyes, ears, and other organs for
sensors; hands,legs, mouth, and other body parts
for actuators
• Robotic agent: cameras and infrared range
finders for sensors;various motors for actuators-
Self Driving Car-Camera(sensors)-Red signal-Hit
the brake to stop-Actuator
Agents and environments
 Agent Function and Agent Program
• The agent function that maps any given percept
histories(sequence) to an actions:
• [f: P*  A]
Agent: Percept*  Action *
The ideal mapping specifies which actions an agent ought
to take at any point in time
• The agent program runs on the physical
architecture to produce agent function f
• Agent = Architecture + Program
 Vacuum-cleaner world

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

• Actions: Left, Right, Suck, NoOp
 A vacuum-cleaner agent
\input{tables/vacuum-agent-function-table}
•
 Rational agents-The Concept of rationality
• A rational agent is an agent whose acts try to maximize
some performance measure.
• An agent should strive to "do the right thing", based on
what it can perceive and the actions it can perform.
• The right action is the one that will cause the agent to be
most successful
• 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.
 Rational agents
• 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.
 Rational agents
• Rationality is distinct from omniscience (all-
knowing with infinite knowledge)

• Agents can perform actions in order to modify

future percepts so as to obtain useful
information (sometimes called information
gathering, exploration)

• An agent is autonomous if its behavior is

determined by its own experience (with ability
to learn and adapt)
• The rationality of an agent depends on four
things
– the performance measure defining the
agent's degree of success
– the percept sequence, the sequence of all the
things perceived by the agent
– the agent's prior knowledge of the
environment
– the actions that the agent can perform
• Rational ≠ omniscient
– percepts may not supply all relevant
information
• Rational ≠ clairvoyant
– action outcomes may not be as expected
• Hence, rational ≠ successful
• Rational ->exploration, learning, autonomy
Agent Faculties
• The fundamental faculties of intelligence are
– Acting
– Sensing
– Understanding, reasoning, learning
Intelligent Agents
An intelligent agent must sense, must act, must be
autonomous(to some extent ), It also must be
rational agent
 Task environment
• To design a rational agent we need to specify
a task environment
– a problem specification for which the agent is a
solution

• PEAS: to specify a task environment

– Performance measure
– Environment
– Actuators
– Sensors
 PEAS: Specifying an automated taxi driver

Performance measure:
–?
Environment:
–?
Actuators:
–?
Sensors:
–?
 PEAS: Specifying an automated taxi driver

Performance measure:
– safe, fast, legal, comfortable, maximize profits
Environment:
–?
Actuators:
–?
Sensors:
–?
 PEAS: Specifying an automated taxi driver

Performance measure:
– safe, fast, legal, comfortable, maximize profits
Environment:
– roads, other traffic, pedestrians, customers
Actuators:
–?
Sensors:
–?
 PEAS: Specifying an automated taxi driver

Performance measure:
– safe, fast, legal, comfortable, maximize profits
Environment:
– roads, other traffic, pedestrians, customers
Actuators:
– steering, accelerator, brake, signal, horn
Sensors:
–?
 PEAS: Specifying an automated taxi driver

Performance measure:
– safe, fast, legal, comfortable, maximize profits
Environment:
– roads, other traffic, pedestrians, customers
Actuators:
– steering, accelerator, brake, signal, horn
Sensors:
– cameras, sonar, speedometer, GPS
 Class Room Activity
• Agent types:
• Medical Diagnostic Systems
• Satellite Image Analysis Systems
• Part Picking Robot
• Refinery Controller
• Interactive English Tutor

Percepts Action Goals Environment

 SearchBot PEAS Description
Performance number of “hits” (relevant retrieved items)
recall (hits / all relevant items)
Measures precision (relevant items/retrieved items)
quality of hits

Environment document repository (data base, files,

WWW, ...)
computer system (hardware, OS, software, ...
network (protocol, interconnection, ...)

Actuators query functions

retrieval functions
display functions

Sensors input parameters

 StudentBot PEAS Description
Performance grade
time spent studying
Measures career success

Environment classroom, university, universe

Actuators human actuators

Sensors human sensors

 Properties of task environments

• [Link] 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 the environment is effectively and
fully observable
• if the sensors detect all aspects
• That are relevant to the choice of action

Task environment-Choice,Action and Outcome

• Partially observable
An environment might be Partially observable because
of noisy and inaccurate sensors or because parts of
the state are simply missing from the sensor data.
Example:
– A local dirt sensor of the cleaner cannot tell
– Whether other squares are clean or not
 Properties of task environments

• [Link] vs. stochastic

– next state of the environment Completely
determined by the current state and the
actions executed by the agent, then the
environment is deterministic, otherwise, it is
Stochastic.

-Cleaner and taxi driver are:

• Stochastic because of some unobservable aspects 
noise or unknown
 Properties of task environments
• [Link] vs. sequential
– An episode = agent’s single pair of perception & action
– The quality of the agent’s action does not depend on other
episodes
• Every episode is independent of each other
– Episodic environment is simpler
• The agent does not need to think ahead
• Sequential
– Current action may affect all future decisions
-Ex. Taxi driving and chess.
 Properties of task environments

• [Link] vs. dynamic

– A dynamic environment is always changing
over time
• E.g., the number of people in the street
– While static environment
• E.g., the destination
• Semidynamic
– environment is not changed over time
– but the agent’s performance score does
 Properties of task environments

• [Link] vs. continuous

– If there are a limited number of distinct states,
clearly defined percepts and actions, the
environment is discrete
– E.g., Chess game
– Continuous: Taxi driving
 Properties of task environments
• [Link] agent VS. multiagent
– Playing a crossword puzzle – single agent
– Chess playing – two agents
– Competitive multiagent environment
• Chess playing
– Cooperative multiagent environment
• Automated taxi driver
• Avoiding collision
 Properties of task environments
• [Link] vs. unknown
This distinction refers not to the environment itself but to the
agent’s (or designer’s) state of knowledge about the
environment.
-In known environment, the outcomes for all actions are
given. ( example: solitaire card games).
- If the environment is unknown, the agent will have to learn
how it works in order to make good decisions.( example: new
video game).
Ex: Crossword puzzle
1. Fully observable/Partially observable :
2. Deterministic/Stochastic :
3. Episodic/Sequential :
4. Static/ Dynamic :
5. Discrete/ Continuous:
6. Single agent/Multi agent :
Examples of task environments
Structure of agents
 Structure of agents
• Agent = architecture + program
– Architecture = some sort of computing device
(sensors + actuators)
– (Agent) Program = some function that implements
the agent mapping = “?”
– Agent Program = Job of AI
 Agent programs
• Input for Agent Program
– Only the current percept
• A sensor could be a camera, an infrared device, a sonar, an
ultrasound, a radar.
• Input for Agent Function
– The entire percept sequence
– The agent must remember all of them
• Implement the agent program as
– A look up table (agent function)
• Actuators : It could be a robot’s legs, wheels, arms, fingers,
wings or fins. Effector are also called “actuators.”
 Agent programs
• Skeleton design of an agent program
 Agent Programs
• P = the set of possible percepts
• T= lifetime of the agent
– The total number of percepts it receives
• Size of the look up table
• The agent function (f) maps from percept (P)
histories to actions (A) will be represented as
f : P* → A.
 Agent programs
• Despite of huge size, look up table does what
we want.
• The key challenge of AI
– Find out how to write programs that, to the
extent possible, produce rational behavior
• From a small amount of code
• Rather than a large amount of table entries
– E.g., a five-line program of Newton’s Method
– V.s. huge tables of square roots, sine, cosine, …
 RULES OF AN AGENT
• Rule 1: Perceive the environment : Analyze the working
environment and gather the required input through
sensors
• Rule 2: Apply environmental observation to make
decision : Based on the observation from the sensors,
Identify the needed actions that has to be performed
• Rule 3: Actuators perform the actions: Off the list of
observations made, the right actions needed to be
chosen and executed
• Rule 4 : Rational decision with maximum performance
and best positive outcome
 TYPES OF AGENTS
• The agents are classified into two categories based on
the characteristics and capability.
• Based on the characteristics the agents are further
divided into six types and they are as follows:
• Proactive Agents
• Reactive Agents
• Dynamic Agents
• Static Agents
• Single Agent
• Multi agent
 Types of agent programs
Based on the capability, the agents are further divided
into
1. Simple Reflex Agents : Works on simple if-then rules
and instant decisions are made
2. Model-Based Agents : Works on rule based system
considering the past events also
3. Goal-Based Agents : Works towards the goal state
4. Utility-Based Agents: Considers the profit of the users
5. Learning Agents : Applies intelligence for reaching the
goals
 Simple reflex agents

• It uses just condition-action rules

– The rules are like the form “if … then …”
– efficient but have narrow range of applicability
– Because knowledge sometimes cannot be stated
explicitly
– Work only
• if the environment is fully observable
 Reflex Agent Diagram

Sensors

Environment
What the world is like now

Condition-action rules
What should I do now

Agent
Actuators
Simple reflex agents
 Reflex Agent Program

function SIMPLE-REFLEX-AGENT(percept) returns

action
static: rules //set of condition-action
rules

condition := INTERPRET-INPUT(percept)
rule := RULE-MATCH(condition, rules)
action := RULE-ACTION(rule)

return action
 A Simple Reflex Agent in Nature
percepts
(size, motion)

RULES:
(1) If small moving object,
then activate SNAP
(2) If large moving object,
then activate AVOID and inhibit SNAP
ELSE (not moving) then NOOP

needed for
completeness Action: SNAP or AVOID or NOOP
 Model-based Reflex Agents

• For the world that is partially observable

– the agent has to keep track of an internal state
• That depends on the percept history
• Reflecting some of the unobserved aspects
• E.g., driving a car and changing lane
• Requiring two types of knowledge
– How the world evolves independently of the agent
– How the agent’s actions affect the world
 Example Table Agent
With Internal State
IF THEN

Saw an object ahead, Go straight

and turned right, and
it’s now clear ahead
Saw an object on my Halt
right, turned right, and
object ahead again
See no objects ahead Go straight

See an object ahead Turn randomly

 Example Reflex Agent With Internal State:
Wall-Following

start

Actions: left, right, straight, open-door

Rules:
1. If open(left) & open(right) and open(straight) then
choose randomly between right and left
2. If wall(left) and open(right) and open(straight) then straight
3. If wall(right) and open(left) and open(straight) then straight
4. If wall(right) and open(left) and wall(straight) then left
5. If wall(left) and open(right) and wall(straight) then right
6. If wall(left) and door(right) and wall(straight) then open-door
7. If wall(right) and wall(left) and open(straight) then straight.
8. (Default) Move randomly
Model-based reflex agents
Model-Based Reflex Agent
Example
 Model-Based Reflex Agent Program
function REFLEX-AGENT-WITH-STATE(percept) returns action
static: rules //set of condition-action rules
state //description of the current world
state
action //most recent action, initially none

state := UPDATE-STATE(state, action, percept)

rule := RULE-MATCH(state, rules)
action := RULE-ACTION[rule]
return action
 Goal-based agents
• Current state of the environment is always not
enough
• The goal is another issue to achieve
– Judgment of rationality / correctness
• Actions chosen  goals, based on
– the current state
– the current percept
 Goal-based agents

• Conclusion
– Goal-based agents are less efficient
– but more flexible
• Agent  Different goals  different tasks
– Search and planning
• two other sub-fields in AI
• to find out the action sequences to achieve its goal
Goal-Based Agent Diagram

Sensors
State What the world is like now

How the world evolves What happens if I do an action

What my actions do

Goals
What should I do now

Agent Actuators

Environment
Goal-based agents
Example
• More Real Time Applications
➢ Search strategies & Planning
➢ GPS navigation in vehicles
➢ AI games
 Utility-based agents

• Goals alone are not enough

– to generate high-quality behavior
– E.g. meals in Canteen, good or not ?
• Many action sequences  the goals
– some are better and some worse
– If goal means success,
– then utility means the degree of success (how
successful it is)
 Utility-based agents
• it is said state A has higher utility
– If state A is more preferred than others
• Utility is therefore a function
– that maps a state onto a real number
– the degree of success
 Utility-based agents (3)
• Utility has several advantages:
– When there are conflicting goals,
• Only some of the goals but not all can be achieved
• utility describes the appropriate trade-off
– When there are several goals
• None of them are achieved certainly
• utility provides a way for the decision-making
Utility-based agents
Example
 Agents
Some general features characterizing agents:

• Autonomy
• goal-orientedness
• collaboration
• flexibility
• ability to be self-starting
• temporal continuity
• character
• adaptiveness
• mobility
• capacity to learn.
 Classification of agents
 Interface Agents
AI techniques to provide assistance to the user
 Mobile agents
capable of moving around networks gathering
information
 Co-operative agents
communicate with, and react to, other agents in a
multi-agent systems within a common environment
 Reactive agents
“reacts” to a stimulus or input that is governed by
some state or event in its environment
 Learning Agents
• After an agent is programmed, can it work
immediately?
– No, it still need teaching
• In AI,
– Once an agent is done
– We teach it by giving it a set of examples
– Test it by using another set of examples
• We then say the agent learns
– A learning agent
 Learning Agents
• Four conceptual components
– Learning element
• Making improvement
– Performance element
• Selecting external actions
– Critic
• Tells the Learning element how well the agent is doing with
respect to fixed performance standard.
(Feedback from user or examples, good or not?)
– Problem generator
• Suggest actions that will lead to new and informative experiences.
Learning agents
Example
 Components of a learner
• In learning, percepts may help improve agent’s
future success in interaction
• Components:
- Learning element (improves policy)
- Performance element (executes policy)
- Critic: Applies fixed performance
measure
- Problem generator: Suggests
experimental actions that will provide
information to learning element
A learning agent and its environment
 Automated taxi example
• Performance element-whatever collection of
knowledge and procedures the taxi has for
selecting its driving actions.
• The taxi goes out on the road and drives, using
this performance element
 Automated taxi example
• Critic-observes the world and passes information
along to the learning element.
• For example, after the taxi makes a quick left turn
across three lanes of traffic, the critic observes the
shocking language used by other drivers.
• From this experience, the learning element is able to
formulate a rule saying this was a bad action, and the
performance element is modified by installation of
the new rule.
 Automated taxi example
• The problem generator- might identify certain areas
of behavior in need of improvement and suggest
experiments, such as trying out the brakes on
different road surfaces under different conditions.
• The Learning element-if the taxi exerts a certain
braking pressure when driving on a wet road, then it
will soon find out how much deceleration is actually
achieved.
• Clearly, these two learning tasks are more difficult if
the environment is only partially observable.
 Automated taxi example
• The situation is slightly more complex for a utility-
based agent that wishes to learn utility information.
For example, suppose the taxi-driving agent receives
no tips from passengers who have been thoroughly
shaken up during the trip.
• The external performance standard must inform the
agent that the loss of tips is a negative contribution
to its overall performance; then the agent might be
able to learn that violent maneuvers do not
contribute to its own utility.
 Automated taxi example
• In a sense, the performance standard distinguishes
part of the incoming percept as a reward (or penalty)
that provides direct feedback on the quality of the
agent’s behavior.
• Hard-wired performance standards such as pain and
hunger in animals can be understood in this way.
 How the components of agent programs
work?
• Question for a student of AI is, “How on earth
do these components work?
 How the components of agent programs
work?
• Agent’s organization
a) Atomic Representation: In this representation, each state of
the world is a black box that has no internal structure. E.g.,
finding each state is a city. AI algorithms: search, games, Markov
decision processes, hidden Markov models, etc.
b) Factored Representation: In this representation, each state has
some attribute value properties. E.g., GPS location, amount of gas
in the tank. AI algorithms: constraint satisfaction, and Bayesian
networks.
c) Structured Representation: Relationships between the objects
of a state can be explicitly expressed. AI algorithms: first-order
logic, knowledge-based learning, natural language understanding.
 The major points to recall are as follows:
• 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 behavior 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.
 The major points to recall are as follows:
• 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.
 Class Room Discussion
• Poster preparation
• For each of the following activities, give a PEAS description of the
task environment and characterize it in terms of the properties
• Playing soccer.
• Exploring the subsurface oceans of Titan.
• Shopping for used AI books on the Internet.
• Playing a tennis match.
• Practicing tennis against a wall.
• Performing a high jump.
• Knitting a sweater.
• Bidding on an item at an auction.