Bibtex
|
ACM
|
MLA
|
APA
|
Harvard
|
Vancouver
|
Chicago
@misc{Christiano2017Deep, title = {{Deep Reinforcement Learning From Human Preferences}}, author = {Christiano, Paul and Leike, Jan and Brown, Tom B. and Martic, Miljan and Legg, Shane and Amodei, Dario}, year = {2017}, publisher = {arXiv}, doi = {10.48550/arXiv.1706.03741}, }
Paul Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep Reinforcement Learning From Human Preferences. arXiv.1706.03741, pp. . DOI: https://doi.org/10.48550/arXiv.1706.03741
Christiano, Paul, Leike, Jan, Brown, Tom B., Martic, Miljan, Legg, Shane, and Amodei, Dario. "Deep Reinforcement Learning From Human Preferences". arXiv.1706.03741, pp. . 2017.
Christiano, P., Leike, J., Brown, T., Martic, M., Legg, S., & Amodei, D. (2017). Deep Reinforcement Learning From Human Preferences. arXiv.1706.03741, pp. .
Christiano, P., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D., 2017. Deep Reinforcement Learning From Human Preferences.arXiv.1706.03741, pp.
Christiano P, Leike J, Brown T, Martic M, Legg S, Amodei D. Deep Reinforcement Learning From Human Preferences.arXiv.1706.037412017; pp. .
Christiano, Paul, Leike, Jan, Brown, Tom B., Martic, Miljan, Legg, Shane, and Amodei, Dario "Deep Reinforcement Learning From Human Preferences". arXiv.1706.03741, pp. . 2017.