AI Collection

Conference item

Loaded DiCE: Trading off bias and variance in any-order score function gradient estimators for reinforcement learning

Publication status:: Published

Peer review status:: Peer reviewed

Actions

Email

Email this record

Send the bibliographic details of this record to your email address.

Your Email
Please enter the email address that the record information will be sent to.

-
Your message (optional)
Please add any additional information to be included within the email.
Share
Cite

Cite this record

APA Style

Farquhar, G., Whiteson, S., & Foerster, J. (2019). Loaded DiCE: Trading off bias and variance in any-order score function gradient estimators for reinforcement learning. 32, 1–12.

MLA Style

Farquhar, G, et al. “Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning.” vol. 32, 2019, pp. 1–12.

Chicago Style

Farquhar, G, S Whiteson, and J Foerster. 2019. “Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning.” 32: 1–12.
Print

Access Document

Files:: dice_main.pdf

(Preview, Accepted manuscript, pdf, 754.3KB, Terms of use)

Authors

+ Farquhar, G More by this author

Role:: Author

+ Whiteson, S More by this author

Institution:: University of Oxford
Division:: MPLS
Department:: Computer Science
Oxford college:: St Catherine's College
Role:: Author

+ Foerster, J More by this author

Role:: Author

+ European Commission More from this funder

Grant:: 637713

Publisher:: Neural Information Processing Systems Foundation
Host title:: NIPS Proceedings
Journal:: NIPS Proceedings More from this journal
Volume:: 32
Pages:: 1-12
Publication date:: 2019-11-18
Acceptance date:: 2019-12-08

Keywords:: FFR
Pubs id:: pubs:1080562
UUID:: uuid:a5e80b4d-2498-4aab-9ee1-c67547ef6764
Local pid:: pubs:1080562
Source identifiers:: 1080562
Deposit date:: 2019-12-31
ARK identifier:: ark:/29072/ora_a5e80b4d24984aab9ee1c67547ef6764

Terms of use

Copyright date:: 2019
Notes:: This paper was presented at the 32nd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, December 2019. This is the accepted manuscript version of the paper. The final version is available online from the Neural Information Processing Systems Foundation at: https://papers.nips.cc/paper/9026-loaded-dice-trading-off-bias-and-variance-in-any-order-score-function-gradient-estimators-for-reinforcement-learning

Licence:: Terms and Conditions of Use for Oxford University Research Archive

Views and Downloads

About views and downloads

If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP