Intelligent Agents

Click to add Text

 Chapter 2
Intelligent Agents
What is an agent ?
 An agent is anything that perceiving its
environment through sensors and acting
upon that environment through actuators
 Example:
 Human is an agent
 A robot is also an agent with cameras and motors

 A thermostat detecting room temperature.

Intelligent Agents
Diagram of an agent

What AI should fill

 Simple Terms
Percept
 Agent’s perceptual inputs at any given instant
Percept sequence
 Complete history of everything that the agent
has ever perceived.
 Vacuum-cleaner world
Perception: Clean or Dirty? where it is in?
Actions: Move left, Move right, suck, do
nothing
Vacuum-cleaner world
 Concept of Rationality
Rational agent
 One that does the right thing
What is correct?
 The actions that cause the agent to be
most successful
 So we need ways to measure success.
 Performance measure
Performance measure
 An objective function that determines
 How the agent does successfully
 E.g., 90% or 30% ?

An agent, based on its percepts

 action sequence :
if desirable, it is said to be performing well.
 No universal performance measure for all

agents
 Rational agent
For each possible percept sequence,
 an rational agent should select
 an action expected to maximize its performance
measure, given the evidence provided by the
percept sequence and whatever built-in knowledge
the agent has
E.g., an exam
 Maximize marks, based on
the questions on the paper & your knowledge
 Autonomy
If an agent just relies on the prior knowledge of
its designer rather than its own percepts then
the agent lacks autonomy
A rational agent should be autonomous- it
should learn what it can to compensate for
partial or incorrect prior knowledge.
E.g., a clock
 No input (percepts)
 Run only but its own algorithm (prior knowledge)
 No learning, no experience, etc.
 Software Agents
Sometimes, the environment may not be
the real world
 E.g.,flight simulator, video games, Internet
 They are all artificial but very complex

environments
 Those agents working in these environments

are called
 Softwareagent (softbots)
 Because all parts of the agent are software
 Task environments
Task environments are the problems
 While the rational agents are the solutions
Specifying the task environment
 PEAS description as fully as possible
 Performance
 Environment

 Actuators

 Sensors

In designing an agent, the first step must always be to

specify the task environment as fully as possible.
Use automated taxi driver as an example
 Task environments
Environment
A taxi must deal with a variety of roads
 Traffic lights, other vehicles, pedestrians,

stray animals, road works, police cars, etc.

 Interact with the customer
 Task environments
Actuators (for outputs)
 Control over the accelerator, steering, gear
shifting and braking
 A display to communicate with the
customers
Sensors (for inputs)
 Detect other vehicles, road situations
 GPS (Global Positioning System) to know
where the taxi is
 Many more devices are necessary
 Task environments
A sketch of automated taxi driver
Properties of task environments
Fully observable vs. Partially observable
 Ifan 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
 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
Deterministic 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.
 Strategic environment: deterministic except for

actions of other agents

-Cleaner and taxi driver are:
 Stochastic because of some unobservable aspects 
noise or unknown
 Properties of task environments
Episodic 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
 EX: part picking robot

Sequential:
It require memory of past action to determine next best action
 Ex. Taxi driving and chess.
Properties of task environments
Static vs. dynamic
A dynamic environment is always changing
over time
 E.g., the number of people in the street,
crossword puzzle
 While static environment
 E.g., the destination, taxi driving
 Properties of task environments

Discrete vs. continuous

 Ifthere are a limited number of distinct
states, clearly defined percepts and actions,
the environment is discrete
 E.g., Chess game

Continuous: Action performed cannot be

numbered
E.g., Self driving car
Properties of task environments

Single agent VS. multiagent

 single agent: only one agent is involved in
an environment and operating by itself
 E.g., maze game

 Multiagent: multiple agent operating in an

environment
 E.g., Football
Properties of task environments

Known vs. unknown

 Known: results of all actions are known.
 E.g., Card game

 Unknown: Agent need to learn how it works

 E.g. Video game

Examples of task environments
Structure of agents

Click to add Text

 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
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)
 Types of agent programs
Four types
 Simple reflex agents
 Model-based reflex agents

 Goal-based agents

 Utility-based agents
 Simple reflex agents
 Takes decision on the basis of current percept
and ignore the rest percept history
 Succeed in fully observable environment

 Not consider any part of percept history during

their decision and action process

 Condition action value

 Ex: room cleaner agent

 Limited knowledge
Simple reflex agents
Simple reflex agents (2)
 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 Ahead, Halt
turned right, and object
ahead again
See no objects ahead Go straight

See an object ahead Turn randomly

Model-based Reflex Agents
 Goal-based agents
Current state of the environment is
always not enough
Needs to know its goal which describes
desirable situation
Having goal information
 the current state
 the current percept

 Ex: Tracking the GPRS location and

searching shortest path

 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 agents
 Utility-based agents
Similar to goal based agent, but having
extra component called utility
measurement
 then utility means the degree of success
(how successful it is)
 The best way to achieve the goals

 Utility function will map each state to a real

number to check how efficiently each

action achieves the goal.
Utility-based agents (4)
 Utility-based agents
it is said state A has higher utility
 If state A is more preferred than others
Utility is therefore a function
 thatmaps a state onto a real number
 the degree of success
 Learning Agents
Learning from past or it has learning
capabilities
 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