@inproceedings{NIPS2017_d5e2c0ad, author = {Christiano, Paul F and Leike, Jan and Brown, Tom and Martic, Miljan and Legg, Shane and Amodei, Dario}, booktitle = {Advances in Neural Information Processing Systems}, editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett}, pages = {}, publisher = {Curran Associates, Inc.}, title = {Deep Reinforcement Learning from Human Preferences}, url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/d5e2c0adad503c91f91df240d0cd4e49-Paper.pdf}, volume = {30}, year = {2017} }