RUDDER: Return Decomposition for Delayed Rewards. Arjona-Medina, J. A, Gillhofer, M., Widrich, M., Unterthiner, T., & Hochreiter, S. , 2018.
bibtex   
@Article{Arjona-Medina2018,
author = {Arjona-Medina, Jose A and Gillhofer, Michael and Widrich, Michael and Unterthiner, Thomas and Hochreiter, Sepp}, 
title = {RUDDER: Return Decomposition for Delayed Rewards}, 
journal = {}, 
volume = {}, 
number = {}, 
pages = {}, 
year = {2018}, 
abstract = {}, 
location = {}, 
keywords = {}}

Downloads: 0