CS344M Autonomous Multiagent Systems Todd Hester Department or - - PowerPoint PPT Presentation

▶
cs344m autonomous multiagent systems
SMART_READER_LITE
LIVE PREVIEW

CS344M Autonomous Multiagent Systems Todd Hester Department or - - PowerPoint PPT Presentation

Apr 30, 2023 196 likes •627 views

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

slide-1
SLIDE 1

CS344M Autonomous Multiagent Systems

Todd Hester Department or Computer Science The University of Texas at Austin

slide-2
SLIDE 2

Good Afternoon, Colleagues

Todd Hester

slide-3
SLIDE 3

Good Afternoon, Colleagues

Are there any questions?

Todd Hester

slide-4
SLIDE 4

Logistics

  • Questions about the syllabus?

Todd Hester

slide-5
SLIDE 5

Logistics

  • Questions about the syllabus?
  • Class registration and waitlist

Todd Hester

slide-6
SLIDE 6

Logistics

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

Todd Hester

slide-7
SLIDE 7

Logistics

  • Questions about the syllabus?
  • Class registration and waitlist
  • Problems with the assignment?
  • Piazza vs. mailing list

Todd Hester

slide-8
SLIDE 8

Logistics

  • Questions about the syllabus?
  • Class registration and waitlist
  • Problems with the assignment?
  • Piazza vs. mailing list

− CC Elad, Patrick, and me on everything

Todd Hester

slide-9
SLIDE 9

Logistics

  • Questions about the syllabus?
  • Class registration and waitlist
  • Problems with the assignment?
  • Piazza vs. mailing list

− CC Elad, Patrick, and me on everything

  • Last week’s slides are up

Todd Hester

slide-10
SLIDE 10

Logistics

  • Questions about the syllabus?
  • Class registration and waitlist
  • Problems with the assignment?
  • Piazza vs. mailing list

− CC Elad, Patrick, and me on everything

  • Last week’s slides are up
  • Next week’s readings are up:

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

Todd Hester

slide-11
SLIDE 11

Logistics

  • Questions about the syllabus?
  • Class registration and waitlist
  • Problems with the assignment?
  • Piazza vs. mailing list

− CC Elad, Patrick, and me on everything

  • Last week’s slides are up
  • Next week’s readings are up:

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

  • Overlap with Intro to AI

Todd Hester

slide-12
SLIDE 12

Logistics

  • Questions about the syllabus?
  • Class registration and waitlist
  • Problems with the assignment?
  • Piazza vs. mailing list

− CC Elad, Patrick, and me on everything

  • Last week’s slides are up
  • Next week’s readings are up:

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

  • Overlap with Intro to AI
  • C/C++ issues

Todd Hester

slide-13
SLIDE 13

Logistics

  • Questions about the syllabus?
  • Class registration and waitlist
  • Problems with the assignment?
  • Piazza vs. mailing list

− CC Elad, Patrick, and me on everything

  • Last week’s slides are up
  • Next week’s readings are up:

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

  • Overlap with Intro to AI
  • C/C++ issues

Todd Hester

slide-14
SLIDE 14

Words without (accepted) definitions

  • Intelligence
  • Agent

Todd Hester

slide-15
SLIDE 15

Words without (accepted) definitions

  • Intelligence
  • Agent

All proposed definitions include too much or leave gaps.

Todd Hester

slide-16
SLIDE 16

Words without (accepted) definitions

  • Intelligence
  • Agent

All proposed definitions include too much or leave gaps. But there are examples. . .

Todd Hester

slide-17
SLIDE 17

Thermostats

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

Todd Hester

slide-18
SLIDE 18

Intelligent (autonomous) Agents

  • Autonomous robot

Todd Hester

slide-19
SLIDE 19

Intelligent (autonomous) Agents

  • Autonomous robot
  • Information gathering agent

− Find me the cheapest?

Todd Hester

slide-20
SLIDE 20

Intelligent (autonomous) Agents

  • Autonomous robot
  • Information gathering agent

− Find me the cheapest?

  • E-commerce agents

− Decides what to buy/sell and does it

Todd Hester

slide-21
SLIDE 21

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

Todd Hester

slide-22
SLIDE 22

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

Todd Hester

slide-23
SLIDE 23

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

Todd Hester

slide-24
SLIDE 24

Not Intelligent Agents

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

Todd Hester

slide-25
SLIDE 25

Your Agent Examples

Todd Hester

slide-26
SLIDE 26

Your Agent Examples

  • Automotive: Stop light, Autonomous Car
  • Physical Control: Roomba, Automatic sliding door
  • Software:

antivirus software, Google Now, Laptop battery management, Macbook light intensity controller, Parasolid

  • Game/entertainment: StarCraft SCV, Counterstrike
  • Service: Stock trading agent

Todd Hester

slide-27
SLIDE 27

An Example

Todd Hester

slide-28
SLIDE 28

An Example

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

Todd Hester

slide-29
SLIDE 29

An Example

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

Todd Hester

slide-30
SLIDE 30

An Example

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

Todd Hester

slide-31
SLIDE 31

An Example

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

Todd Hester

slide-32
SLIDE 32

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

Todd Hester

slide-33
SLIDE 33

How did you do it?

Todd Hester

slide-34
SLIDE 34

How did you do it?

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

Todd Hester

slide-35
SLIDE 35

Formalizing My Example

Knowns:

Todd Hester

slide-36
SLIDE 36

Formalizing My Example

Knowns:

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

Todd Hester

slide-37
SLIDE 37

Formalizing My Example

Knowns:

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

Unknowns:

Todd Hester

slide-38
SLIDE 38

Formalizing My Example

Knowns:

  • O = {Blue, Red, Green, Black, . . .}
  • 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

Todd Hester

slide-39
SLIDE 39

Formalizing My Example

Knowns:

  • O = {Blue, Red, Green, Black, . . .}
  • 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)

Todd Hester

slide-40
SLIDE 40

Formalizing My Example

Knowns:

  • O = {Blue, Red, Green, Black, . . .}
  • 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)

Todd Hester

slide-41
SLIDE 41

Formalizing My Example

Knowns:

  • O = {Blue, Red, Green, Black, . . .}
  • 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)

Todd Hester