[PDF] - Administrative Issues Login into learn.usc.edu and make sure Login PDF Document

SLIDE 1

1

Administrative Issues

Login into learn usc edu and make sure

Login into learn.usc.edu and make sure

that CSCI561a is listed as one of your courses.

Web page: Web page:

http://www-scf.usc.edu/~ csci561b/ http://den.usc.edu

Acting Humanly: The Full Turing Test

Problem:

1) Turing test is not reproducible, constructive, and amenable to mathematic analysis. 2) What about physical interaction with interrogator and environment?

Trap door

SLIDE 2

2

Last time: The Turing Test

http://www.ai.mit.edu/projects/infolab/ http://aimovie.warnerbros.com

This time: Outline

Intelligent Agents (IA)

Intelligent Agents (IA) Environment types IA Behavior IA Structure

IA T

IA Types

SLIDE 3

3

Attributes of Intelligent Behavior

Think and reason Use reason to solve problems Learn or understand from experience Acquire and apply knowledge Exhibit creativity and imagination Deal with complex or perplexing situations Respond quickly and successfully to new

it ti situations.

Recognize the relative importance of elements

in a situation

Handle ambiguous, incomplete,or erroneous

information

Intelligent Agents

Interface Tutors Search Agents Presentation Agents Network Navigation A t User Interface Agents Information Management Agents Information Brokers Agents Role- Playing Agents Information Filters

SLIDE 4

4

What is an (Intelligent) Agent?

An over used over loaded and

An over-used, over-loaded, and

misused term.

Anything that can be viewed as

perceiving its environment

p g

acting upon that environment

What is an (Intelligent) Agent?

PAGE (Percepts Actions Goals

PAGE (Percepts, Actions, Goals,

Environment)

Task-specific & specialized: well-defined

goals and environment g

SLIDE 5

5

Intelligent Agents and Artificial Intelligence

Example: Human mind as network of

p thousands or millions of agents working in parallel.

Agency sensors effectors

Agent Types

Agent research fall into two main strands: Agent research fall into two main strands:

Distributed Artificial Intelligence (DAI) –

Multi-Agent Systems (MAS) (1980 – 1990)

Much broader notion of "agent"

(1990’s – present)

SLIDE 6

6

Rational Agents

Ho to design this? Environment A percepts ? Sensors How to design this? Agent actions Effectors

A Windshield Wiper Agent

How do we design an agent that can wipe How do we design an agent that can wipe the windshields when needed?

Goals? Percepts ?

S ?

Sensors? Effectors ? Actions ? Environment ?

SLIDE 7

7

Grand Challenge

Autonomous Driving

Interacting Agents

Collision Avoidance Agent (CAA)

Goals:

Avoid running into obstacles

Percepts ? Sensors? Effectors ? Actions ? Environment:

Freeway

SLIDE 8

8

Interacting Agents

Lane Keeping Agent (LKA)

Goals:

Stay in current lane

Percepts ?
Sensors?
Effectors ?

Effectors ?

Actions ?
Environment:

Freeway

Conflict Resolution by Action Selection Agents

Override:

Override:

Arbitrate:
Compromise:
Challenges:

SLIDE 9

9

The Right Thing = The Rational Action

Rational Action: The action that maximizes the Rational Action: The action that maximizes the

expected value of the performance measure given the percept sequence to date

Rational = Best ? Rational = Optimal ?

R ti l O i i ? (H i t t l

Rational = Omniscience ? (Having total

knowledge)

Rational = Clairvoyant ? (The sixth sense) Rational = Successful ?

Behavior and performance of IAs

Perception (sequence) to Action

Mapping: f : P* → A

I deal mapping:

SLIDE 10

10

Look up table

bstacle

sensor

Distance Acttion

agent sensor

Distance Acttion 10 No action 5 Turn left 30 5 Turn left 30 degrees 2 Stop

Closed form

Output (degree of rotation) =

F(distance)

SLIDE 11

11

Behavior and performance of IAs

Performance measure:

(d f) A t

(degree of) Autonomy:

How is an Agent different from other software?

Agents are autonomous Agents are autonomous, Agents contain some level of intelligence, Agents don't only act reactively, but

sometimes also proactively

SLIDE 12

12

How is an Agent different from other software?

Agents have social ability, Agents may cooperate with other agents Agents may migrate from one system to

another

Environment Types

Characteristics

Accessible vs. inaccessible Deterministic vs. nondeterministic Episodic vs. nonepisodic (Sequential)

SLIDE 13

13

Environment Types

Characteristics

Hostile vs. friendly Static vs. dynamic Discrete vs. continuous

Environment types

Environment Accessi Determinis Episodic Static Discrete Environment Accessi ble Determinis tic Episodic Static Discrete Operating System Virtual Reality Offi Office Environment Mars

SLIDE 14

14

Structure of Intelligent Agents

Agent = architecture + program

Agent = architecture + program Agent program: the implementation

f f : P* → A, the agent’s perception-

action mapping

function: Skeleton-Agent(Percept) returns Action memory ← UpdateMemory(memory, Percept) Action ← ChooseBestAction(memory) memory ← UpdateMemory(memory, Action) return Action

Using a look-up-table to encode f : P* → A

Example: Collision Avoidance

p

Sensors:

3 proximity sensors

Effectors:

Steering Wheel, Brakes

How to generate? How large? How to select action?

agent

bstacle

sensors

SLIDE 15

15

Using a look-up-table to encode f : P* → A

b t l

Example: Collision Avoidance

Sensors:

3 proximity sensors

Effectors:

Steering Wheel, Brakes

agent

bstacle

sensors

Using a look-up-table to encode f : P* → A

How large: How large: How to select action? Is it an autonomous agent? (by using the

look up table)

SLIDE 16

16

Agent types

Reflex agents

g

Reactive: No memory

Reflex agents with internal states Goal-based agents

Goal information needed to make decision

Agent types

Utility-based agents

y g

Learning Agent

SLIDE 17

17

Reflex agents Question

Design a group of mobile robots that

stay together and move around using reactive (reflex) agents?

SLIDE 18

18

Reflex agents w/ state (model-based reflex agent) Goal-based agents

SLIDE 19

19

Utility-based agents Learning agents

Performance standard Performance element Learning element Critic Changes l d feedback Learning Problem generator Knowledge Learning goal

SLIDE 20

20

Information agents

Manage the explosive growth of information.

Information agents

Examples:

BargainFinder comparison shops among

Internet stores for CDs

FIDO the Shopping Doggie (out of service) Internet Softbot infers which internet

facilities (finger, ftp, gopher) to use and when from high-level search requests.

Challenge: ontologies for annotating

Web pages (eg, SHOE).

SLIDE 21

21

Example: ALADDIN project

Autonomous Learning Agents for Decentralized Data and Information Network

http://www aladdinproject org/technolo

http://www.aladdinproject.org/technolo

gies.html

Online evacuation algorithm

Based on sensors, provide guidance to

people.

Rescue planning

Detecting injured and update all (using

NN)

Summary

I ntelligent Agents:

Anything that can be viewed as perceiving its

environment through sensors and acting

upon that environment through its effectors to maximize progress towards its goals. PAGE (P t A ti G l E i t)

PAGE (Percepts, Actions, Goals, Environment) Described as a Perception (sequence) to

Action Mapping: f : P* → A

Using look-up-table, closed form, etc.

SLIDE 22

22

Summary

Agent Types: Reflex state based goal

Agent Types: Reflex, state-based, goal-

based, utility-based, Learning

Rational Action: The action that