@inproceedings{NEURIPS2019_16105fb9, author = {Arjona-Medina, Jose A. and Gillhofer, Michael and Widrich, Michael and Unterthiner, Thomas and Brandstetter, Johannes and Hochreiter, Sepp}, booktitle = {Advances in Neural Information Processing Systems}, editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett}, pages = {}, publisher = {Curran Associates, Inc.}, title = {RUDDER: Return Decomposition for Delayed Rewards}, url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/16105fb9cc614fc29e1bda00dab60d41-Paper.pdf}, volume = {32}, year = {2019} }