Lecture 2 Flashcards

1
Q

What is an Agent?

A

Anything that perceives its
environment through sensors and
acts upon it through actuators

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What sensors and actuators does a “human agent” have?

A
  • Sensors: Eyes, ears, etc.
  • Actuators: Hands, legs, vocal tract
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are percepts?

A

The content an agent’s sensors are receiving.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What is a percept sequence?

A

The complete history of everything
the agent has perceived.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

What is an Agent function?

A

A mapping of any given percept
sequence to an action

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

What is an agent program?

A

A concrete implementation to
realize an agent function internally

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

How should a rational agent select an action?

A

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 about the environment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is the task environment?

A

The “problems” to which rational agents are the “solutions.”

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What is the acronym for task environment?

A
  • Performance measures: How desirable is the sequence of environments the
    agent has experienced?
  • Environment: What are the key elements in the surroundings of the agent
    that can influence the agent?
  • Actuators: What allows the agent to take actions?
  • Sensors: What allows the agent to perceive its surroundings?
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

What does it mean for an environment to be partially observable?

A

An agent’s sensors do not have access to the complete state of the environment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What does it mean for an environment to be multi-agent?

A

There are multiple agents in the environment

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What does it mean for an environment to be stochastic?

A

The environment is unpredictable

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What does it mean for an environment to be dynamic?

A

The environment changes over time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What does it mean for an environment to be continuous?

A

Relevant precepts and actions aer. continuous, ex: speed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

What does it mean for an environment to be fully observable?

A

The agent’s sensors give it access to the complete state of the environment at any point in time

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What does it mean for an environment to be fully deterministic?

A

The next state of the environment is completely determined by the current
state and the action executed by the agent. (non stochastic)

17
Q

What does it mean for an environment to be static?

A

The environment itself does not change with the passage of time

18
Q

What does it mean for an environment to be discrete?

A

The environment has a discrete set of precepts and actions

19
Q

What are some environment properties of a Crossword Puzzle?

A

Fully observable, single agent,
deterministic, static, discrete

20
Q

What are some environment properties of Image analysis?

A

Fully observable, single agent,
deterministic, semi, continuous

21
Q

What are some environment properties of a Part-picking robot?

A

Partially observable, single agent,
stochastic, dynamic, continuous

22
Q

How does a simple reflex agent work?

A

Has no memory of the environment, simply uses sensors and picks action.

23
Q

How does a model based agent work?

A

Uses an internal state to keep track of the environment.

24
Q

How does a goal based agent work?

A

Predicts result of action and whether it satisfies happy or not happy goal.

25
Q

How does a Utility-based agent work?

A

A full rational agent that analyzes action effect on utility and tries to maximize it.

26
Q

What is an atomic state representation?

A

Like one to one I guess ex: West Lafayette

27
Q

What is a factored state representation?

A

Multiple scales ex: current speed, current state

28
Q

What is a structured state representation?

A

Has objects and relations