CS344M Autonomous Multiagent Systems Patrick MacAlpine Department - - PowerPoint PPT Presentation

▶
cs344m autonomous multiagent systems
SMART_READER_LITE
LIVE PREVIEW

CS344M Autonomous Multiagent Systems Patrick MacAlpine Department - - PowerPoint PPT Presentation

Mar 31, 2024 228 likes •587 views

CS344M Autonomous Multiagent Systems Patrick MacAlpine Department or Computer Science The University of Texas at Austin Good Afternoon, Colleagues Patrick MacAlpine Good Afternoon, Colleagues Are there any questions? Patrick MacAlpine

slide-1
SLIDE 1

CS344M Autonomous Multiagent Systems

Patrick MacAlpine Department or Computer Science The University of Texas at Austin

slide-2
SLIDE 2

Good Afternoon, Colleagues

Patrick MacAlpine

slide-3
SLIDE 3

Good Afternoon, Colleagues

Are there any questions?

Patrick MacAlpine

slide-4
SLIDE 4

Logistics

  • Questions about the syllabus?

Patrick MacAlpine

slide-5
SLIDE 5

Logistics

  • Questions about the syllabus?
  • Class registration

Patrick MacAlpine

slide-6
SLIDE 6

Logistics

  • Questions about the syllabus?
  • Class registration
  • Problems with the assignment?

Patrick MacAlpine

slide-7
SLIDE 7

Logistics

  • Questions about the syllabus?
  • Class registration
  • Problems with the assignment?
  • Piazza and Canvas — announcements yesterday

Patrick MacAlpine

slide-8
SLIDE 8

Logistics

  • Questions about the syllabus?
  • Class registration
  • Problems with the assignment?
  • Piazza and Canvas — announcements yesterday
  • Last week’s slides are up

Patrick MacAlpine

slide-9
SLIDE 9

Logistics

  • Questions about the syllabus?
  • Class registration
  • Problems with the assignment?
  • Piazza and Canvas — announcements yesterday
  • Last week’s slides are up
  • Next week’s readings are up:

− Brooks’ reactive robots − A more deliberative architecture − RoboCup challenge paper

Patrick MacAlpine

slide-10
SLIDE 10

Logistics

  • Questions about the syllabus?
  • Class registration
  • Problems with the assignment?
  • Piazza and Canvas — announcements yesterday
  • Last week’s slides are up
  • Next week’s readings are up:

− Brooks’ reactive robots − A more deliberative architecture − RoboCup challenge paper

  • Seating arrangement

Patrick MacAlpine

slide-11
SLIDE 11

Thermostats

  • Are they agents or not?
  • How does Wooldridge resolve this?

Patrick MacAlpine

slide-12
SLIDE 12

Intelligent (autonomous) Agents

  • Autonomous robot

Patrick MacAlpine

slide-13
SLIDE 13

Intelligent (autonomous) Agents

  • Autonomous robot
  • Information gathering agent

− Find me the cheapest?

Patrick MacAlpine

slide-14
SLIDE 14

Intelligent (autonomous) Agents

  • Autonomous robot
  • Information gathering agent

− Find me the cheapest?

  • E-commerce agents

− Decides what to buy/sell and does it

Patrick MacAlpine

slide-15
SLIDE 15

Intelligent (autonomous) Agents

  • Autonomous robot
  • Information gathering agent

− Find me the cheapest?

  • E-commerce agents

− Decides what to buy/sell and does it

  • Air-traffic controller

Patrick MacAlpine

slide-16
SLIDE 16

Intelligent (autonomous) Agents

  • Autonomous robot
  • Information gathering agent

− Find me the cheapest?

  • E-commerce agents

− Decides what to buy/sell and does it

  • Air-traffic controller
  • Meeting scheduler

Patrick MacAlpine

slide-17
SLIDE 17

Intelligent (autonomous) Agents

  • Autonomous robot
  • Information gathering agent

− Find me the cheapest?

  • E-commerce agents

− Decides what to buy/sell and does it

  • Air-traffic controller
  • Meeting scheduler
  • Computer-game-playing agent

Patrick MacAlpine

slide-18
SLIDE 18

Not Intelligent Agents

  • Thermostat
  • Telephone
  • Answering machine
  • Pencil
  • Java object

Patrick MacAlpine

slide-19
SLIDE 19

Your Agent Examples

Patrick MacAlpine

slide-20
SLIDE 20

Your Agent Examples

Simple home alarm; cat food dispenser Software: anti-virus/malware agent; spam filter; web crawler; iOS autocorrect daemon Automotive: smart keys; digitial highway speed sign; traffic light with sensors; autonomous car; cruise control Telecom: GPS device; cell phone Physical Control: Roomba; lawn watering system Health: pacemaker Game/Entertainment: chess player; first person shooter AI

Patrick MacAlpine

slide-21
SLIDE 21

An Example

Patrick MacAlpine

slide-22
SLIDE 22

An Example

  • You, as a class, act as a learning agent

Patrick MacAlpine

slide-23
SLIDE 23

An Example

  • You, as a class, act as a learning agent
  • Actions: Wave, Stand, Clap

Patrick MacAlpine

slide-24
SLIDE 24

An Example

  • You, as a class, act as a learning agent
  • Actions: Wave, Stand, Clap
  • Observations: colors, reward

Patrick MacAlpine

slide-25
SLIDE 25

An Example

  • You, as a class, act as a learning agent
  • Actions: Wave, Stand, Clap
  • Observations: colors, reward
  • Goal: Find an optimal policy

Patrick MacAlpine

slide-26
SLIDE 26

An Example

  • You, as a class, act as a learning agent
  • Actions: Wave, Stand, Clap
  • Observations: colors, reward
  • Goal: Find an optimal policy

− Way of selecting actions that gets you the most reward

Patrick MacAlpine

slide-27
SLIDE 27

How did you do it?

Patrick MacAlpine

slide-28
SLIDE 28

How did you do it?

  • What is your policy?
  • What does the world look like?

Patrick MacAlpine

slide-29
SLIDE 29

Formalizing My Example

Knowns:

Patrick MacAlpine

slide-30
SLIDE 30

Formalizing My Example

Knowns:

  • O = {Blue, Red, Green, Yellow, . . .}
  • Rewards in IR
  • A = {Wave, Clap, Stand}
  • 0, a0, r0, o1, a1, r1, o2, . . .

Patrick MacAlpine

slide-31
SLIDE 31

Formalizing My Example

Knowns:

  • O = {Blue, Red, Green, Yellow, . . .}
  • Rewards in IR
  • A = {Wave, Clap, Stand}
  • 0, a0, r0, o1, a1, r1, o2, . . .

Unknowns:

Patrick MacAlpine

slide-32
SLIDE 32

Formalizing My Example

Knowns:

  • O = {Blue, Red, Green, Yellow, . . .}
  • Rewards in IR
  • A = {Wave, Clap, Stand}
  • 0, a0, r0, o1, a1, r1, o2, . . .

Unknowns:

  • S = 4x3 grid
  • R : S × A → IR
  • P = S → O
  • T : S × A → S

Patrick MacAlpine

slide-33
SLIDE 33

Formalizing My Example

Knowns:

  • O = {Blue, Red, Green, Yellow, . . .}
  • Rewards in IR
  • A = {Wave, Clap, Stand}
  • 0, a0, r0, o1, a1, r1, o2, . . .

Unknowns:

  • S = 4x3 grid
  • R : S × A → IR
  • P = S → O
  • T : S × A → S
  • i = P(si)

Patrick MacAlpine

slide-34
SLIDE 34

Formalizing My Example

Knowns:

  • O = {Blue, Red, Green, Yellow, . . .}
  • Rewards in IR
  • A = {Wave, Clap, Stand}
  • 0, a0, r0, o1, a1, r1, o2, . . .

Unknowns:

  • S = 4x3 grid
  • R : S × A → IR
  • P = S → O
  • T : S × A → S
  • i = P(si)

ri = R(si, ai)

Patrick MacAlpine

slide-35
SLIDE 35

Formalizing My Example

Knowns:

  • O = {Blue, Red, Green, Yellow, . . .}
  • Rewards in IR
  • A = {Wave, Clap, Stand}
  • 0, a0, r0, o1, a1, r1, o2, . . .

Unknowns:

  • S = 4x3 grid
  • R : S × A → IR
  • P = S → O
  • T : S × A → S
  • i = P(si)

ri = R(si, ai) si+1 = T (si, ai)

Patrick MacAlpine