lecture 1

Question 1

agent

Answer 1

perceiving its environment (throgh sensors) and acting upon the envirnment (through actuators)

Question 2

human agent

Answer 2

environment: the world in which we are embodied.
sensors: eyes, ears, nose.
actuators : hands, legs, voice.

Question 3

robotic agent

Answer 3

environment: the (part of the) world in which it is embodied.
sensors: (infrared) cameras, mic, temp sensors.
actuators: various motors and output devices.

Question 4

sowftware agent:

Answer 4

environment: software that it interacts with, including IO.
sensors: keystrokes, networl packages, file contents.
actuators: writing to files, screen display.

Question 5

Genral AI

Answer 5

building machines that can perform any intelectual task as well as or better the humans

Question 6

Narrow AI

Answer 6

building machines that can perform a specific intellectual task very well.

Question 7

Physical symbol system hypothesis

Answer 7

A physical system has the necessary and sufficient means for general intelligent action.

• A symbol is a meaningful physical pattern that can be manipulated.
• A symbol systen creates, copies, modifies and destroys symbols.

Question 8

The chinese room arguement

Answer 8

Assuming that a computer can fool us into thinking its human, does that mean that it is intelligent.
“The computer doesn’t think, it just follows rules.

Question 9

optimal solution

Answer 9

best solution according some measure of solution quality

Question 10

satisficing solution

Answer 10

one that is good enogh, according to some description of which solutions are adequare

Question 11

approx. optimal solution

Answer 11

one whose measure of quality is close to the best theoretically possible

Question 12

probable solution

Answer 12

one that is likely to be a solution.

Question 13

rational agent

Answer 13

Goal is to find optimal solution

Question 14

bounded rationality

Answer 14

Goal is to find a solution that is as best as possible given limitations (time, memory, energy)

Question 15

Abilities

Answer 15

the set of possible actions it can perform

Question 16

goals

Answer 16

what it wants, its desires, its value

Question 17

prior knowledge

Answer 17

what it comes into being knowing, what it doesnt get from experience

Question 18

history of stimuli

Answer 18

current stimuli - what it recieves from the environment now (observation, percepts)
past experiences - what it has received in the past.

Question 19

body and controller

Answer 19

an agent interacts with the environment through its body.
the body id made up of: *sensors that interpret stimuli
*actuators that carry out actions.

• the controller receives percepts from the body and the controller sends commands to the body.

Question 20

controller

Answer 20

the controller is the brain of the agent.

agents are situated in time, they receive sensory data in time, and do actions in time.

controleers have (limitied) memoryy and (limited) computational capabiltiies.

the controller specifies the command at every time.

the comman at any time depend on the current and previous percepts (its history).

Question 21

Belief state

Answer 21

an agent doe’snt have access to its entire history., it only has access to what it has remembered.

the memory or belief state of an agent at times encodes all of the agent’s history that it has access to.

the belief state of an agent encapsulates the info avbout its past that it can use for current anf future actions.

at every time a controller has to decide on: what should it do?
what should it remember?

Question 22

flat

Answer 22

one level of abstraction

Question 23

modular

Answer 23

interacting modules that can be understood separately

Question 24

hierarchical

Answer 24

moduls that are (recursively) decomposd into modules

• flat representations are adequate for simple systems.
• complex bio systems, computer systems, organizations are all hierarchocal

Question 25

kind of agents

Answer 25

• dead reckoning agent: doesnt prceive the world
• reactive agent: doesnt have a belief state.
• model free agent: agent maintains belief state that is used to maximize utility/reward.
• model based agent: agent uses model of the world as belief state to plan optimal actions.