2 - agents Flashcards

1
Q

Agent - definition and explanation

A

an AGENT is anything that can be viewed as percieving an enviroment - so it can read the world through senses and react based on the input sensors recieve

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

rational agent

A

a system that maximazes its performance measure based on the percept sequence and built-in knowledge

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

Task Environment Specification

A

(PEAS) - Performance measure, Environment, Actuators, Sensors

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

percept

A

the agents’ input

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

percept sequence

A

complete history of everything the agent percieved

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

agent function

A

maps given percept sequence into an action

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

agent program

A

runs the physical architecture

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

Table-driven agent

A

daunting sizes of tables, physcial agents cannot store

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

Simple reflex agent

A

selection based only on current perception; condition-action rules => if - then algorithms

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Model based reflex agent

A

has an internal state, storing apsects of the enviroment that cant be immediently observed - keeps that knowledge, comapres current state and adapts

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

Goal based

A

select actions in current state to complete the goal

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

Utility based agent

A

evaluate the desireability of states resulting from each possible action by mapping states onto a number

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

Learning/autonomous agent

A

methods for selecting actions - teach instead of instructing

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

Fully observable vs. partially observable

A

Do the agent’s sensors give it access to the complete state of the environment?

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

Deterministic vs.stochastic

A

Is the next state of the environment completely determined by the current state
and the agent’s action?

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

Episodic vs. sequential

A

Is the agent’s expereince divided into individual episodes or is it a sequence of observations and actions?

17
Q

Static vs. dynamic

A

Is the enviroment changing while the agent is thinking?

18
Q

Discrete vs. continuous

A

Does the enviroment have a fixed number of distinct percepts?

19
Q

Single agent vs. multi-agent

A

Is the agent operating by itself in the enviroment?