Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Intelligent Agents

Lecture 2
by

fadzlan yusuf

on 12 March 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Intelligent Agents

QUIZ AI has succesfully been used in?
i. Finance
ii. Robotics
iii. Games
iv. Medicine
v. Technology
vi. None of them Input 3 Intelligent Agents Output Process Agent Definition
Intelligent Agent
Type of Intelligent Agent
Type of Environments
Task Environments - PEAS (Performance measures, Environment, Actuators and Sensors ) Able to understand what is agent and intelligent agent and how it interacts with environment
Able to explain the different type of agent in AI Systems
Understand the performance measures used in evaluate an agent Intelligent Agents Lecture 2 Any question? Q & A Abdul Rahman Mat, FCSIT Thank You ~End of Session~ Abdul Rahman Mat, FCSIT Summary Abdul Rahman Mat, FCSIT ability to learn enough built-in knowledge to survive To survive, agents must have: A system is autonomous to the extent that its own behavior is determined by its own experience & knowledge. Autonomy Abdul Rahman Mat, FCSIT Are software entities that carry out some set of operations on behalf of a user or another program with some degree of independence or autonomy, and in doing so, employ some knowledge or representation of the user’s goals or desires [IBM White Paper, 1995] Is an entity that can be viewed as perceiving its environment through sensors and acting upon its environment through effectors [Russel & Norvig, 1995]

Human Agent, Robot Agent
Human Agent – Sensors : eyes, ears – Actuators : hands, legs, mouth• Robotic Agent – Sensors ? infra red range finder, camera Actuators: Motor What is Intelligence Agents? What is an Agent? Agent & Intelligent Agent Abdul Rahman Mat, FCSIT Normally operate in dynamic and unpredictable environments. May sometimes be remotely operated by a human (can see what the robot sees through its camera, directly control the movement, and actions of the robot). To do routine tasks in hazardous environments (e.g. as the surface of Mars, at nuclear power station, near a fire). To take some objects to some location somewhere in the building, navigate their way about the building (avoiding obstacles on the way) and make the delivery. Used as “delivery boys” in large organizations. Autonomous Mobile Robots Abdul Rahman Mat, FCSIT Agents-based Interface Information Agents Mail Handling Agents Several kinds of software agents: Software Agents Abdul Rahman Mat, FCSIT Physical Agent Software Agent Intelligent Agent Agent Keys Abdul Rahman Mat, FCSIT Semester 2 - 2012/2013 #Week 2#
Intelligent Agent Abdul Rahman Mat, FCSIT For full flexibility - 6 joints (allows the effector to be placed in any position within reach, at any angle); 6 degrees of freedom: three for x-y-z position & three for orientation. Number & arrangement of the joints determines the range of positions and orientations that the end effector can be positioned in. Consists of a jointed arm with a device or end effector at the end of it (i.e.: gripper – to pick things up) Currently used in a variety of manufacturing tasks (e.g.: welding, assembly, spray painting) Manufacturing Robots Abdul Rahman Mat, FCSIT humanoid robots Autonomous mobile robots Manufacturing robots Type of robots (based on different purposes): Robots: Have its own goals and will be able to adapt its behavior based on information received. relatively simple programmable manipulators used for tasks (e.g.: car assembly, humanoid robots) Physical Agents Abdul Rahman Mat, FCSIT NLP - to analyze potentially relevant tasks ML - to build & update the personal profile ES - to identify relevant information Techniques: Based on personal profile giving the user’s interest, will searches to find relevant information, collate & prioritize the information, & present it to the user on request Information Agents Abdul Rahman Mat, FCSIT Machine Learning: the agent can adapt & improve its behavior Vision: to make sense of the physical environment Knowledge Representation: represent required knowledge Expert System: solve specialized problems NLP: communicate with user Techniques: Planning: what to do Designing Intelligent Agent Abdul Rahman Mat, FCSIT Operate in the physical world & can perceive & manipulate objects. i.e. robots Operate within the confines of the computer / computer network. Physical Agents Software Agents Intelligent Agent Abdul Rahman Mat, FCSIT ML NLP Techniques: Might using forward chaining inference engine to process the rules & deal with the messages IF subject-line includes “TME2073” THEN put into “TME2073Folder” Example: A simple system, allow each person to enter rules which specify how mail should be treated; Needs to have some knowledge of the roles & interests of the people Automatically filter & classify mail Mail Handling Agents Abdul Rahman Mat, FCSIT TOPIO (developed at TOSY Robotics, Vietnam) ASIMO (developed at Honda, Japan) Cog (developed at MIT by Rodney Brooks and team) Example Human-like robots: complete with head, eyes, arms, hands, fingers, and possibly even legs. Humanoid Robots Abdul Rahman Mat, FCSIT Programming paradigm that encourages thinking in terms of communicating agents Agent-oriented programming KR ML NLP Techniques: Need to communicate with other agents in a system (mail handling & information agents) Use info about the user’s particular needs, preferences, factual info about user & organization Conversational agent: is an animated “talking head” that the user can communicate using NL Based on idea the user communicates with one of a no. of conversational agents Agent-based Interface Abdul Rahman Mat, FCSIT Pro-active (goal-directed) Re-active to the environment Interacts with other agents & the environment Autonomous Properties: User delegates responsibility for some of their routine tasks to agent, ensuring the tasks are carried out. Personal assistants to filter mail, find useful docs., schedule meetings & do shopping. Example: Is an independent software component which (typically) provides support for a user of a computer system.
Sensors? Actuators? Software Agents Abdul Rahman Mat, FCSIT Act independently, communicate with other agents, modify what it is doing in response to what it sees and hears Goal: Buy some carrots ii. Agent for do shopping i. Travel Agency Act independently, booking everything (flight to-fro, hotel, transportation, etc) – need to communicate with other agent & recommend anything (related Umrah’s tasks) where appropriate Initial goal: Go for Umrah, Mekah, Saudi Arabia Task: Booking a flight ticket & facilities in order to go for vacation oversea. Example: Agent Abdul Rahman Mat, FCSIT Agent Environment Four basic types in order of increasing generality:
Simple reflex agents
Reflex agents with state/model
Goal-based agents
Utility-based agents
All these can be turned into learning agents
http://www.ai.sri.com/~oreilly/aima3ejava/aima3ejavademos.html Artificial Intelligence a modern approach Agent types Abdul Rahman Mat, FCSIT Able to understand what is agent and intelligent agent and how it operates with the environment
Able to understand the different type of agent in AI systems
Understand the performance measures used in evaluate an agent Thank You ~End of Session~ Abdul Rahman Mat, FCSIT Summary Abdul Rahman Mat, FCSIT Artificial Intelligence a modern approach Utility-based agents Simple but very limited intelligence.
Action does not depend on percept history, only on current percept.
Therefore no memory requirements.
Infinite loops
Suppose vacuum cleaner does not observe location. What do you do given location = clean? Left of A or right on B -> infinite loop.
Fly buzzing around window or light.
Possible Solution: Randomize action.
Thermostat.
Chess – openings, endings
Lookup table (not a good idea in general)
35100 entries required for the entire game Artificial Intelligence a modern approach Simple reflex agents Agent: Interactive English tutor
Performance measure: Maximize student's score on test
Environment: Set of students
Actuators: Screen display (exercises, suggestions, corrections)
Sensors: Keyboard Artificial Intelligence a modern approach PEAS Agent: Part-picking robot
Performance measure: Percentage of parts in correct bins
Environment: Conveyor belt with parts, bins
Actuators: Jointed arm and hand
Sensors: Camera, joint angle sensors Artificial Intelligence a modern approach PEAS Rationality
Performance measuring success
Agents prior knowledge of environment
Actions that agent can perform
Agent’s percept sequence to date

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.

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 Artificial Intelligence a modern approach Rational agents Abdul Rahman Mat, FCSIT AI has successfully been used in?
Finance
Robotics
Games
Medicine
Technology
None of them POP QUIZ Any question? Q & A Abdul Rahman Mat, FCSIT Artificial Intelligence a modern approach Performance element
How it currently drives
Taxi driver Makes quick left turn across 3 lanes
Critics observe shocking language by passenger and other drivers and informs bad action
Learning element tries to modify performance elements for future
Problem generator suggests experiment out something called Brakes on different Road conditions
Exploration vs. Exploitation
Learning experience can be costly in the short run
shocking language from other drivers
Less tip
Fewer passengers Learning agents(Taxi driver) Performance element is what was previously the whole agent
Input sensor
Output action
Learning element
Modifies performance element. Artificial Intelligence a modern approach Learning agents Goals are not always enough
Many action sequences get taxi to destination
Consider other things. How fast, how safe…..
A utility function maps a state onto a real number which describes the associated degree of “happiness”, “goodness”, “success”.
Where does the utility measure come from?
Economics: money.
Biology: number of offspring.
Your life? Artificial Intelligence a modern approach Utility-based agents

Reflex agent breaks when it sees brake lights. Goal based agent reasons
Brake light -> car in front is stopping -> I should stop -> I should use brake Artificial Intelligence a modern approach Goal-based agents knowing state and environment? Enough?
Taxi can go left, right, straight
Have a goal
A destination to get to
Uses knowledge about a goal to guide its actions
E.g., Search, planning Artificial Intelligence a modern approach Goal-based agents Fully observable (vs. partially observable)
Deterministic (vs. stochastic)
Episodic (vs. sequential)
Static (vs. dynamic)
Discrete (vs. continuous)
Single agent (vs. multiagent): Artificial Intelligence a modern approach Environment types PEAS: Performance measure, Environment, Actuators, Sensors

Must first specify the setting for intelligent agent design

Consider, e.g., the task of designing an automated taxi driver:

Performance measure: Safe, fast, legal, comfortable trip, maximize profits

Environment: Roads, other traffic, pedestrians, customers

Actuators: Steering wheel, accelerator, brake, signal, horn

Sensors: Cameras, sonar, speedometer, GPS, odometer, engine sensors, keyboard Artificial Intelligence a modern approach PEAS The autonomy of an agent is the extent to which its
behaviour is determined by its own experience,
rather than knowledge of designer. Extremes
No autonomy – ignores environment/data
Complete autonomy – must act randomly/no program
Example: baby learning to crawl
Ideal: design agents to have some autonomy
Possibly become more autonomous with experience Autonomy in Agents Rational is different from omniscience
Percepts may not supply all relevant information
E.g., in card game, don’t know cards of others.

Rational is different from being perfect
Rationality maximizes expected outcome while perfection maximizes actual outcome. Artificial Intelligence a modern approach Rationality Critic: how the agent is doing
Input: checkmate?
Fixed

Problem generator
Tries to solve the problem differently instead of optimizing.
Suggests exploring new actions -> new problems. Artificial Intelligence a modern approach Learning agents Artificial Intelligence a modern approach Simple reflex agents Know how world evolves
Overtaking car gets closer from behind
How agents actions affect the world
Wheel turned clockwise takes you right

Model base agents update their state Artificial Intelligence a modern approach Model-based reflex agents Physical Agent
Type of Intelligent Agent
Type of Environments
Task Environments – PEAS (Perfromace measure, Environment, Actuators and Sensors Software Agent Intelligent Agent Agent Definition Keys Abdul Rahman Mat, FCSIT ENVIRONMENT AGENT Abdul Rahman Mat, FCSIT Demo: http://www.ai.sri.com/~oreilly/aima3ejava/aima3ejavademos.html
Percepts: location and contents, e.g., [A,Dirty]
Actions: Left, Right, Suck, NoOp
Agent’s function  look-up table
For many agents this is a very large table Artificial Intelligence a modern approach Vacuum-cleaner world For full flexibility - 6 joints (allows the effector to be placed in any position within reach, at any angle); 6 degrees of freedom: three for x-y-z position & three for orientation. Number & arrangement of the joints determines the range of positions and orientations that the end effector can be positioned in. Consists of a jointed arm with a device or end effector at the end of it (i.e.: gripper – to pick things up) Currently used in a variety of manufacturing tasks (e.g.: welding, assembly, spray painting) Manufacturing Robots Abdul Rahman Mat, FCSIT Agents-based Interface Information Agents Mail Handling Agents Several kinds of software agents: Software Agents Abdul Rahman Mat, FCSIT ability to learn enough built-in knowledge to survive To survive, agents must have: A system is autonomous to the extent that its own behavior is determined by its own experience & knowledge. Autonomy Abdul Rahman Mat, FCSIT Operate in the physical world & can perceive & manipulate objects. i.e. robots Operate within the confines of the computer / computer network. Physical Agents Software Agents Intelligent Agent Abdul Rahman Mat, FCSIT Are software entities that carry out some set of operations on behalf of a user or another program with some degree of independence or autonomy, and in doing so, employ some knowledge or representation of the user’s goals or desires [IBM White Paper, 1995] Is an entity that can be viewed as perceiving its environment through sensors and acting upon its environment through effectors [Russel & Norvig, 1995] What is Intelligence Agents? What is an Agent? Agent & Intelligent Agent Abdul Rahman Mat, FCSIT Semester 1 - 2012/2013 #Week 2#
Intelligent Agent TME2073
Sistem Pintar
Intelligent Systems Abdul Rahman Mat, FCSIT Normally operate in dynamic and unpredictable environments. May sometimes be remotely operated by a human (can see what the robot sees through its camera, directly control the movement, and actions of the robot). To do routine tasks in hazardous environments (e.g. as the surface of Mars, at nuclear power station, near a fire). To take some objects to some location somewhere in the building, navigate their way about the building (avoiding obstacles on the way) and make the delivery. Used as “delivery boys” in large organizations. Autonomous Mobile Robots Abdul Rahman Mat, FCSIT NLP - to analyze potentially relevant tasks ML - to build & update the personal profile ES - to identify relevant information Techniques: Based on personal profile giving the user’s interest, will searches to find relevant information, collate & prioritize the information, & present it to the user on request Information Agents Abdul Rahman Mat, FCSIT Machine Learning: the agent can adapt & improve its behavior Vision: to make sense of the physical environment Knowledge Representation: represent required knowledge Expert System: solve specialized problems NLP: communicate with user Techniques: Planning: what to do Designing Intelligent Agent Abdul Rahman Mat, FCSIT TOPIO (developed at TOSY Robotics, Vietnam) ASIMO (developed at Honda, Japan) Cog (developed at MIT by Rodney Brooks and team) Example Human-like robots: complete with head, eyes, arms, hands, fingers, and possibly even legs. Humanoid Robots Abdul Rahman Mat, FCSIT humanoid robots Autonomous mobile robots Manufacturing robots Type of robots (based on different purposes): Robots: Have its own goals and will be able to adapt its behavior based on information received. relatively simple programmable manipulators used for tasks (e.g.: car assembly, humanoid robots) Physical Agents Abdul Rahman Mat, FCSIT ML NLP Techniques: Might using forward chaining inference engine to process the rules & deal with the messages IF subject-line includes “TME2073” THEN put into “TME2073Folder” Example: A simple system, allow each person to enter rules which specify how mail should be treated; Needs to have some knowledge of the roles & interests of the people Automatically filter & classify mail Mail Handling Agents Abdul Rahman Mat, FCSIT Pro-active (goal-directed) Re-active to the environment Interacts with other agents & the environment Autonomous Properties: User delegates responsibility for some of their routine tasks to agent, ensuring the tasks are carried out. Personal assistants to filter mail, find useful docs., schedule meetings & do shopping. Example: Is an independent software component which (typically) provides support for a user of a computer system
Sensors? Actuators? Software Agents Abdul Rahman Mat, FCSIT no yes yes no Uncertainty Certainty: Search Deterministic Fully Observable Artificial Intelligence a modern approach Choice under (Un)certainty Programming paradigm that encourages thinking in terms of communicating agents Agent-oriented programming KR ML NLP Techniques: Need to communicate with other agents in a system (mail handling & information agents) Use info about the user’s particular needs, preferences, factual info about user & organization Conversational agent: is an animated “talking head” that the user can communicate using NL Based on idea the user communicates with one of a no. of conversational agents Agent-based Interface Abdul Rahman Mat, FCSIT Multi Multi Multi Single Single Single Image analysis Poker Part picking robot Taxi driver Backgammon Cross Word An agent operating by itself in an environment or there are many agents working together Artificial Intelligence a modern approach Single agent (vs. multiagent): \ Semi Dynamic Dynamic Static Static Static Image analysis Poker Part picking robot Taxi driver Backgammon Cross Word Static environments don’t change
While the agent is deliberating over what to do
Dynamic environments do change
So agent should/could consult the world when choosing actions
Alternatively: anticipate the change during deliberation OR make decision very fast
Semidynamic: If the environment itself does not change with the passage of time but the agent's performance score does. Artificial Intelligence a modern approach Static (vs. dynamic): Act independently, communicate with other agents, modify what it is doing in response to what it sees and hears Goal: Buy some carrots ii. Agent for do shopping i. Travel Agency Act independently, booking everything (flight to-fro, hotel, transportation, etc) – need to communicate with other agent & recommend anything (related Umrah’s tasks) where appropriate Initial goal: Go for Umrah, Mekah, Saudi Arabia Task: Booking a flight ticket & facilities in order to go for vacation oversea. Example: Agent Abdul Rahman Mat, FCSIT Conti Conti Conti Discrete Discrete Discrete Image analysis Poker Part picking robot Taxi driver Backgammon Cross Word A limited number of distinct, clearly defined percepts and actions vs. a range of values (continuous) Artificial Intelligence a modern approach Discrete (vs. continuous) Episodic Episodic Sequential Sequential Sequential Sequential Image analysis Poker Part picking robot Taxi driver Backgammon Cross Word Is the choice of current action
Dependent on previous actions?
If not, then the environment is episodic
In non-episodic environments:
Agent has to plan ahead:
Current choice will affect future actions Artificial Intelligence a modern approach Episodic (vs. sequential): Partially Partially Partially Fully Fully Fully Image analysis Poker Part picking robot Taxi driver Backgammon Cross Word Is everything an agent requires to choose its actions available to it via its sensors? Perfect or Full information.
If so, the environment is fully accessible
If not, parts of the environment are inaccessible
Agent must make informed guesses about world.
In decision theory: perfect information vs. imperfect information. Artificial Intelligence a modern approach Fully observable (vs. partially observable) Stochastic Stochastic Stochastic Stochastic Deterministic Deterministic Cross Word Image analysis Poker Part picking robot Taxi driver Backgammon Does the change in world state
Depend only on current state and agent’s action?
Non-deterministic environments
Have aspects beyond the control of the agent
Utility functions have to guess at changes in world Artificial Intelligence a modern approach Deterministic (vs. stochastic) Partially Partially Partially Fully Fully Fully Summary. Multi Multi Multi Single Single Single Conti Conti Conti Discrete Discrete Discrete Semi Dynamic Dynamic Static Static Static Episodic Episodic Sequential Sequential Sequential Sequential Stochastic Stochastic Stochastic Deterministic Stochastic Deterministic Image analysis Poker Part picking robot Taxi driver Backgammon Cross Word Discrete Agents Episodic Static Deterministic Observable Artificial Intelligence a modern approach OUTPUT
Full transcript