Asset Details
Do you wish to reserve the book?
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds
Do you wish to request the book?
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
Sample complexity of variance-reduced policy gradient: weaker assumptions and lower bounds
2024
Overview
Several variance-reduced versions of REINFORCE based on importance sampling achieve an improved
O
(
ϵ
-
3
)
sample complexity to find an
ϵ
-stationary point, under an unrealistic assumption on the variance of the importance weights. In this paper, we propose the Defensive Policy Gradient (DEF-PG) algorithm, based on defensive importance sampling, achieving the same result without any assumption on the variance of the importance weights. We also show that this is not improvable by establishing a matching
Ω
(
ϵ
-
3
)
lower bound, and that REINFORCE with its
O
(
ϵ
-
4
)
sample complexity is actually optimal under weaker assumptions on the policy class. Numerical simulations show promising results for the proposed technique compared to similar algorithms based on vanilla importance sampling.
Publisher
Springer US,Springer Nature B.V
