I2ai at TU München | Flashcards & Summaries

Lernmaterialien für i2ai an der TU München

Greife auf kostenlose Karteikarten, Zusammenfassungen, Übungsaufgaben und Altklausuren für deinen i2ai Kurs an der TU München zu.

TESTE DEIN WISSEN

Agent function

Lösung anzeigen
TESTE DEIN WISSEN

Maps any given percept sequence to an action

Lösung ausblenden
TESTE DEIN WISSEN

Rational Agent

Lösung anzeigen
TESTE DEIN WISSEN

Maximize its performance measure, given the prior percept sequence and its built-in knowledge

Lösung ausblenden
TESTE DEIN WISSEN

Omniscient agent

Lösung anzeigen
TESTE DEIN WISSEN

Knows the actual outcome of its actions, which is impossible in reality. 


Example: Just imagine you know the outcome of betting money on something.

A rational agent (unequal omniscient agent) maximizes expected performance.

Lösung ausblenden
TESTE DEIN WISSEN

Learning

Lösung anzeigen
TESTE DEIN WISSEN

Rational agents are able to learn from perception, i.e., they improve their knowledge of the environment over time.

Lösung ausblenden
TESTE DEIN WISSEN

Autonomy

Lösung anzeigen
TESTE DEIN WISSEN

Rational agent is autonomous if 

  • less dependent on prior knowledge
  • uses newly learned abilities instead.
Lösung ausblenden
TESTE DEIN WISSEN

Task Environment:

PEAS

Lösung anzeigen
TESTE DEIN WISSEN

performance, 

environment,

actuators,

sensors

Lösung ausblenden
TESTE DEIN WISSEN

Properties of Task Environments

Lösung anzeigen
TESTE DEIN WISSEN
  • Fully observable vs.partially observable
  • Single agent vs.multi agent
  • Deterministic vs.stochastic
  • Episodic vs.sequential
  • Discrete vs.continuous
  • Static vs.dynamic
  • Known vs.unknown
Lösung ausblenden
TESTE DEIN WISSEN

Properties of Task Environments:

Fully observable vs.partially observable

Lösung anzeigen
TESTE DEIN WISSEN

Fully observable

Agent can detect the complete state of the environment

Partially observable otherwise.


Example: The vacuum-cleaner world is partially observable since the robot only knows whether the current square is dirty.

Lösung ausblenden
TESTE DEIN WISSEN

Properties of Task Environments:

Single agent vs.multi agent

Lösung anzeigen
TESTE DEIN WISSEN

Multi agent environment

Contains several agents

Single agent environment otherwise. 


Example: The vacuum-cleaner world is a single agent environment. A chess game is a two-agent environment.

Lösung ausblenden
TESTE DEIN WISSEN

Properties of Task Environments:

Deterministic vs.stochastic

Lösung anzeigen
TESTE DEIN WISSEN

Deterministic

Next state is fully determined by its current state and the action of the agent

Stochastic otherwise.


Example: The automated taxi driver environment is stochastic since the behavior of other traffic participants is unpredictable. The outcome of a calculator is deterministic.

Lösung ausblenden
TESTE DEIN WISSEN

Properties of Task Environments:

Episodic vs.sequential

Lösung anzeigen
TESTE DEIN WISSEN

Episodic

actions taken in one episode (in which the robot senses and acts) does not affect later episodes

Sequential otherwise. 

Example: Detecting defective parts on a conveyor belt is episodic. Chess and automated taxi driving are sequential.

Lösung ausblenden
TESTE DEIN WISSEN

Percept sequence

Lösung anzeigen
TESTE DEIN WISSEN

Complete history of its perception

Vacuum cleaner example: [A,Dirty],[A,Clean],[B,Clean],[A,Clean].

Lösung ausblenden
  • 356343 Karteikarten
  • 8254 Studierende
  • 335 Lernmaterialien

Beispielhafte Karteikarten für deinen i2ai Kurs an der TU München - von Kommilitonen auf StudySmarter erstellt!

Q:

Agent function

A:

Maps any given percept sequence to an action

Q:

Rational Agent

A:

Maximize its performance measure, given the prior percept sequence and its built-in knowledge

Q:

Omniscient agent

A:

Knows the actual outcome of its actions, which is impossible in reality. 


Example: Just imagine you know the outcome of betting money on something.

A rational agent (unequal omniscient agent) maximizes expected performance.

Q:

Learning

A:

Rational agents are able to learn from perception, i.e., they improve their knowledge of the environment over time.

Q:

Autonomy

A:

Rational agent is autonomous if 

  • less dependent on prior knowledge
  • uses newly learned abilities instead.
Mehr Karteikarten anzeigen
Q:

Task Environment:

PEAS

A:

performance, 

environment,

actuators,

sensors

Q:

Properties of Task Environments

A:
  • Fully observable vs.partially observable
  • Single agent vs.multi agent
  • Deterministic vs.stochastic
  • Episodic vs.sequential
  • Discrete vs.continuous
  • Static vs.dynamic
  • Known vs.unknown
Q:

Properties of Task Environments:

Fully observable vs.partially observable

A:

Fully observable

Agent can detect the complete state of the environment

Partially observable otherwise.


Example: The vacuum-cleaner world is partially observable since the robot only knows whether the current square is dirty.

Q:

Properties of Task Environments:

Single agent vs.multi agent

A:

Multi agent environment

Contains several agents

Single agent environment otherwise. 


Example: The vacuum-cleaner world is a single agent environment. A chess game is a two-agent environment.

Q:

Properties of Task Environments:

Deterministic vs.stochastic

A:

Deterministic

Next state is fully determined by its current state and the action of the agent

Stochastic otherwise.


Example: The automated taxi driver environment is stochastic since the behavior of other traffic participants is unpredictable. The outcome of a calculator is deterministic.

Q:

Properties of Task Environments:

Episodic vs.sequential

A:

Episodic

actions taken in one episode (in which the robot senses and acts) does not affect later episodes

Sequential otherwise. 

Example: Detecting defective parts on a conveyor belt is episodic. Chess and automated taxi driving are sequential.

Q:

Percept sequence

A:

Complete history of its perception

Vacuum cleaner example: [A,Dirty],[A,Clean],[B,Clean],[A,Clean].

i2ai

Erstelle und finde Lernmaterialien auf StudySmarter.

Greife kostenlos auf tausende geteilte Karteikarten, Zusammenfassungen, Altklausuren und mehr zu.

Jetzt loslegen

Das sind die beliebtesten StudySmarter Kurse für deinen Studiengang i2ai an der TU München

Für deinen Studiengang i2ai an der TU München gibt es bereits viele Kurse, die von deinen Kommilitonen auf StudySmarter erstellt wurden. Karteikarten, Zusammenfassungen, Altklausuren, Übungsaufgaben und mehr warten auf dich!

Das sind die beliebtesten i2ai Kurse im gesamten StudySmarter Universum

IA

Fachhochschule Aachen

Zum Kurs
i2dl

TU München

Zum Kurs

Die all-in-one Lernapp für Studierende

Greife auf Millionen geteilter Lernmaterialien der StudySmarter Community zu
Kostenlos anmelden i2ai
Erstelle Karteikarten und Zusammenfassungen mit den StudySmarter Tools
Kostenlos loslegen i2ai