Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Exercicio 8.1 #42

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Exercicio 8.1 #42

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions Capítulo 8/Ex8.1.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
Exercise 8.1 The nonplanning method looks particularly poor in Figure 8.3 because it is
a one-step method; a method using multi-step bootstrapping would do better. Do you
think one of the multi-step bootstrapping methods from Chapter 7 could do as well as
the Dyna method? Explain why or why not.


O Dyna-Q sintetiza todas as experiências anteriores para alguns estados escolhidos de forma aleatória. Já o n-step bootstrapping
pode ser mais lento para convergir, pois atualiza apenas os últimos estados visitados. No entanto, existe um maior desperdício de computação no Dyna-Q,
pois alguns estados aleatórios que não são importantes serão atualizados. Portanto, o Dyna-Q consegue propagar de volta as recompensas
recebidas para estados anteriores na etapa de planejamento, já o n-step propaga para estados visitados anteriormente.