Search Header Logo

Quiz RL - Deep Q Learning

Authored by meilana siswanto

Computers

University

Used 3+ times

Quiz RL - Deep Q Learning
AI

AI Actions

Add similar questions

Adjust reading levels

Convert to real-world scenario

Translate activity

More...

    Content View

    Student View

10 questions

Show all answers

1.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Control SARSA terinspirasi dari:

Policy evaluation

Policy Iteration

Value iteration

Value evaluation

2.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Control Q Learning terinspirasi dari:

Policy iteration

Policy evaluation

Value iteration

Value evaluation

3.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Control DQ Learning terinspirasi dari:

Policy iteration

Value iteration

Artificial Neural Network

Artificial Neural Network & Q Learning

4.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Perbedaan antara Control Q Learning dengan SARSA terletak pada:

Epsilon - Greedy Policy

Greedy Policy

Exploitation Policy

Exploitation - Greedy Policy

5.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Q-value function memiliki input berupa:

state

value

state value

state action

6.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Q-value function memiliki output berupa:

state

value

state value

state action

7.

MULTIPLE CHOICE QUESTION

30 sec • 1 pt

Eksplorasi pada pemilihan action berguna untuk:

Memilih episode terbaik dari state berikut

Memilih value terbaik dari state berikut

Memilih value terbesar dari state berikut

Memilih action lain dari state tersebut

Access all questions and much more by creating a free account

Create resources

Host any resource

Get auto-graded reports

Google

Continue with Google

Email

Continue with Email

Classlink

Continue with Classlink

Clever

Continue with Clever

or continue with

Microsoft

Microsoft

Apple

Apple

Others

Others

Already have an account?